Video_Caption
-
Interpretable Traffic Responsibility from Dashcam Video via Legal Multi Agent Reasoning
Abstract
The widespread adoption of dashcams has made video evidence in traffic accidents increasingly abundant, yet transforming "what happened in the video" into "who is responsible under which legal provisions" still relies heavily on human experts. Existing ego-view traffic accident studies mainly focus on perception and semantic understanding, while LLM-based legal methods are mostly built on textual case descriptions and rarely incorporate video evidence, leaving a clear gap between the two. We first propose C-TRAIL, a multimodal legal dataset that, under the Chinese traffic regulation system, explicitly aligns dashcam videos and textual descriptions with a closed set of responsibility modes and their corresponding Chinese traffic statutes. On this basis, we introduce a two-stage framework: (1) a traffic accident understanding module that generates textual video descriptions; and (2) a legal multi-agent framework that outputs responsibility modes, statute sets, and complete judgment reports. Experimental results on C-TRAIL and MM-AU show that our method outperforms general and legal LLMs, as well as existing agent-based approaches, while providing a transparent and interpretable legal reasoning process.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17930
PDF
-
Video Understanding: From Geometry and Semantics to Unified Models
2026-03-18 15:31:47Zhaochong An, Zirui Li, Mingqiao Ye, Feng Qiao, Jiaang Li, Zongwei Wu, Vishal Thengane, Chengzu Li, Lei Li, Luc Van Gool, Guolei Sun, Serge BelongieAbstract
Video understanding aims to enable models to perceive, reason about, and interact with the dynamic visual world. In contrast to image understanding, video understanding inherently requires modeling temporal dynamics and evolving visual context, placing stronger demands on spatiotemporal reasoning and making it a foundational problem in computer vision. In this survey, we present a structured overview of video understanding by organizing the literature into three complementary perspectives: low-level video geometry understanding, high-level semantic understanding, and unified video understanding models. We further highlight a broader shift from isolated, task-specific pipelines toward unified modeling paradigms that can be adapted to diverse downstream objectives, enabling a more systematic view of recent progress. By consolidating these perspectives, this survey provides a coherent map of the evolving video understanding landscape, summarizes key modeling trends and design principles, and outlines open challenges toward building robust, scalable, and unified video foundation models.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17840
PDF
-
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
2026-03-18 15:28:07Yuhao Dong, Zuyan Liu, Shulin Tian, Yongming Rao, Ziwei LiuAbstract
Large Language Models (LLMs) have achieved remarkable reliability and advanced capabilities through extended test-time reasoning. However, extending these capabilities to Multi-modal Large Language Models (MLLMs) remains a significant challenge due to a critical scarcity of high-quality, long-chain reasoning data and optimized training pipelines. To bridge this gap, we present a unified multi-agent visual reasoning framework that systematically evolves from our foundational image-centric model, Insight-V, into a generalized spatial-temporal architecture, Insight-V++. We first propose a scalable data generation pipeline equipped with multi-granularity assessment that autonomously synthesizes structured, complex reasoning trajectories across image and video domains without human intervention. Recognizing that directly supervising MLLMs with such intricate data yields sub-optimal results, we design a dual-agent architecture comprising a reasoning agent to execute extensive analytical chains, and a summary agent to critically evaluate and distill final outcomes. While our initial framework utilized Direct Preference Optimization (DPO), its off-policy nature fundamentally constrained reinforcement learning potential. To overcome these limitations, particularly for long-horizon video understanding, Insight-V++ introduces two novel algorithms, ST-GRPO and J-GRPO, which enhance spatial-temporal reasoning and improve evaluative robustness. Crucially, by leveraging reliable feedback from the summary agent, we guide an iterative reasoning path generation process, retraining the entire multi-agent system in a continuous, self-improving loop. Extensive experiments on base models like LLaVA-NeXT and Qwen2.5-VL demonstrate significant performance gains across challenging image and video reasoning benchmarks while preserving strong capabilities on traditional perception-focused tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2603.18118
PDF
-
M2P: Improving Visual Foundation Models with Mask-to-Point Weakly-Supervised Learning for Dense Point Tracking
2026-03-18 15:06:22Qiangqiang Wu, Tianyu Yang, Bo Fang, Jia Wan, Matias Di Martino, Guillermo Sapiro, Antoni B. ChanAbstract
Tracking Any Point (TAP) has emerged as a fundamental tool for video understanding. Current approaches adapt Vision Foundation Models (VFMs) like DINOv2 via offline finetuning or test-time optimization. However, these VFMs rely on static image pre-training, which is inherently sub-optimal for capturing dense temporal correspondence in videos. To address this, we propose Mask-to-Point (M2P) learning, which leverages rich video object segmentation (VOS) mask annotations to improve VFMs for dense point tracking. Our M2P introduces three new mask-based constraints for weakly-supervised representation learning. First, we propose a local structure consistency loss, which leverages Procrustes analysis to model the cohesive motion of points lying within a local structure, achieving more reliable point-to-point matching learning. Second, we propose a mask label consistency (MLC) loss, which enforces that sampled foreground points strictly match foreground regions across frames. The proposed MLC loss can be regarded as a regularization, which stabilizes training and prevents convergence to trivial solutions. Finally, mask boundary constrain is applied to explicitly supervise boundary points. We show that our weaklysupervised M2P models significantly outperform baseline VFMs with efficient training by using only 3.6K VOS training videos. Notably, M2P achieves 12.8% and 14.6% performance gains over DINOv2-B/14 and DINOv3-B/16 on the TAP-Vid-DAVIS benchmark, respectively. Moreover, the proposed M2P models are used as pre-trained backbones for both test-time optimized and offline fine-tuned TAP tasks, demonstrating its potential to serve as general pre-trained models for point tracking. Code will be made publicly available upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17813
PDF
-
Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos
2026-03-18 13:10:47Songtao Jiang, Sibo Song, Chenyi Zhou, Yuan Wang, Ruizhe Chen, Tongkun Guan, Ruilin Luo, Yan Zhang, Zhihang Tang, Yuchong Sun, Hang Zhang, Zhibo Yang, Shuai Bai, Junyang Lin, Zuozhu LiuAbstract
The transition from image to video understanding requires vision-language models (VLMs) to shift from recognizing static patterns to reasoning over temporal dynamics such as motion trajectories, speed changes, and state transitions. Yet current post-training methods fall short due to two critical limitations: (1) existing datasets often lack temporal-centricity, where answers can be inferred from isolated keyframes rather than requiring holistic temporal integration; and (2) training data generated by proprietary models contains systematic errors in fundamental temporal perception, such as confusing motion directions or misjudging speeds. We introduce SynRL, a post-training framework that teaches models temporal primitives, the fundamental building blocks of temporal understanding including direction, speed, and state tracking. Our key insight is that these abstract primitives, learned from programmatically generated synthetic videos, transfer effectively to real-world scenarios. We decompose temporal understanding into short-term perceptual primitives (speed, direction) and long-term cognitive primitives, constructing 7.7K CoT and 7K RL samples with ground-truth frame-level annotations through code-based video generation. Despite training on simple geometric shapes, SynRL achieves substantial improvements across 15 benchmarks spanning temporal grounding, complex reasoning, and general video understanding. Remarkably, our 7.7K synthetic CoT samples outperform Video-R1 with 165K real-world samples. We attribute this to fundamental temporal skills, such as tracking frame by frame changes and comparing velocity, that transfer effectively from abstract synthetic patterns to complex real-world scenarios. This establishes a new paradigm for video post-training: video temporal learning through carefully designed synthetic data provides a more cost efficient scaling path.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17693
PDF
-
FACE-net: Factual Calibration and Emotion Augmentation for Retrieval-enhanced Emotional Video Captioning
2026-03-18 07:53:15Weidong Chen, Cheng Ye, Zhendong Mao, Peipei Song, Xinyan Liu, Lei Zhang, Xiaojun Chang, Yongdong ZhangAbstract
Emotional Video Captioning (EVC) is an emerging task, which aims to describe factual content with the intrinsic emotions expressed in videos. Existing works perceive global emotional cues and then combine with video content to generate descriptions. However, insufficient factual and emotional cues mining and coordination during generation make their methods difficult to deal with the factual-emotional bias, which refers to the factual and emotional requirements being different in different samples on generation. To this end, we propose a retrieval-enhanced framework with FActual Calibration and Emotion augmentation (FACE-net), which through a unified architecture collaboratively mines factual-emotional semantics and provides adaptive and accurate guidance for generation, breaking through the compromising tendency of factual-emotional descriptions in all sample learning. Technically, we firstly introduces an external repository and retrieves the most relevant sentences with the video content to augment the semantic information. Subsequently, our factual calibration via uncertainty estimation module splits the retrieved information into subject-predicate-object triplets, and self-refines and cross-refines different components through video content to effectively mine the factual semantics; while our progressive visual emotion augmentation module leverages the calibrated factual semantics as experts, interacts with the video content and emotion dictionary to generate visual queries and candidate emotions, and then aggregates them to adaptively augment emotions to each factual semantics. Moreover, to alleviate the factual-emotional bias, we design a dynamic bias adjustment routing module to predict and adjust the degree of bias of a sample.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17455
PDF
-
Shot-Aware Frame Sampling for Video Understanding
2026-03-18 05:36:57Mengyu Zhao, Di Fu, Yongyu Xie, Jiaxing Zhang, Zhigang Yuan, Shirin Jalali, Yong CaoAbstract
Video frame sampling is essential for efficient long-video understanding with Vision-Language Models (VLMs), since dense inputs are costly and often exceed context limits. Yet when only a small number of frames can be retained, existing samplers often fail to balance broad video coverage with brief but critical events, which can lead to unreliable downstream predictions. To address this issue, we present InfoShot, a task-agnostic, shot-aware frame sampler for long-video understanding. InfoShot first partitions a video into semantically consistent shots, and then selects two complementary keyframes from each shot: one to represent the main content and one to capture unusual within-shot changes. This design is guided by an information-theoretic objective that encourages the sampled set to retain high information about both shot structure and sparse within-shot deviations. In this way, it improves the chance of preserving both overall video context and short decision-critical moments without requiring any retraining. To better evaluate such short-lived events, we further introduce SynFlash, a synthetic benchmark with controllable sub-second anomaly patterns and frame-level ground truth, and we also evaluate InfoShot on existing anomaly datasets and general video understanding tasks. Experiments show that InfoShot improves anomaly hit rate and downstream Video-QA accuracy under frame number constraints, while matching or outperforming strong baselines on standard video understanding benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17374
PDF
-
Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress
2026-03-18 03:13:29Yuelin Zhang, Sijie Cheng, Chen Li, Zongzhao Li, Yuxin Huang, Yang Liu, Wenbing HuangAbstract
Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video understanding capabilities, while neglecting their complex reasoning potential. Furthermore, processing long video trajectories with VLMs is computationally prohibitive for real-world deployment. To address these challenges, we propose the Recurrent Reasoning Vision-Language Model ($\text{R}^2$VLM). Our model features a recurrent reasoning framework that processes local video snippets iteratively, maintaining a global context through an evolving Chain of Thought (CoT). This CoT explicitly records task decomposition, key steps, and their completion status, enabling the model to reason about complex temporal dependencies. This design avoids the high cost of processing long videos while preserving essential reasoning capabilities. We train $\text{R}^2$VLM on large-scale, automatically generated datasets from ALFRED and Ego4D. Extensive experiments on progress estimation and downstream applications, including progress-enhanced policy learning, reward modeling for reinforcement learning, and proactive assistance, demonstrate that $\text{R}^2$VLM achieves strong performance and generalization, achieving a new state-of-the-art in long-horizon task progress estimation. The models and benchmarks are publicly available at \href{this https URL}{huggingface}.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17312
PDF
-
Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding
2026-03-18 03:04:49Haiyang Yan, Hongyun Zhou, Peng Xu, Xiaoxue Feng, Mengyi LiuAbstract
Despite rapid developments and widespread applications of MLLM agents, they still struggle with long-form video understanding (LVU) tasks, which are characterized by high information density and extended temporal spans. Recent research on LVU agents demonstrates that simple task decomposition and collaboration mechanisms are insufficient for long-chain reasoning tasks. Moreover, directly reducing the time context through embedding-based retrieval may lose key information of complex problems. In this paper, we propose Symphony, a multi-agent system, to alleviate these limitations. By emulating human cognition patterns, Symphony decomposes LVU into fine-grained subtasks and incorporates a deep reasoning collaboration mechanism enhanced by reflection, effectively improving the reasoning capability. Additionally, Symphony provides a VLM-based grounding approach to analyze LVU tasks and assess the relevance of video segments, which significantly enhances the ability to locate complex problems with implicit intentions and large temporal spans. Experimental results show that Symphony achieves state-of-the-art performance on LVBench, LongVideoBench, VideoMME, and MLVU, with a 5.0% improvement over the prior state-of-the-art method on LVBench. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17307
PDF
-
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
2026-03-17 18:04:58Shenzhi Wang, Shixuan Liu, Jing Zhou, Chang Gao, Xiong-Hui Chen, Binghai Wang, An Yang, Shiji Song, Bowen Yu, Gao Huang, Junyang LinAbstract
VLMs show strong multimodal capabilities, but they still struggle with fine-grained vision-language reasoning. We find that long CoT reasoning exposes diverse failure modes, including perception, reasoning, knowledge, and hallucination errors, which can compound across intermediate steps. However, most existing vision-language data used for RLVR does not involve complex reasoning chains that rely on visual evidence throughout, leaving these weaknesses largely unexposed. We therefore propose HopChain, a scalable framework for synthesizing multi-hop vision-language reasoning data specifically for RLVR training of VLMs. Each synthesized multi-hop query forms a logically dependent chain of instance-grounded hops, where earlier hops establish the instances, sets, or conditions needed for later hops, while the final answer remains a specific, unambiguous number suitable for verifiable rewards. We add the multi-hop data synthesized by HopChain to the original RLVR data used to train Qwen3.5-35B-A3B and Qwen3.5-397B-A17B, and compare against RLVR on the original RLVR data alone across 24 benchmarks spanning STEM and Puzzle, General VQA, Text Recognition and Document Understanding, and Video Understanding. Although this multi-hop data is not synthesized to target any specific benchmark, adding it improves 20 out of 24 benchmarks on both models, indicating broad and generalizable gains. To demonstrate that full chained queries are important, we replace them with half-multi-hop or single-hop variants, reducing the 24-benchmark average accuracy by 5.3 and 7.0 points, respectively. Multi-hop training also strengthens long-CoT vision-language reasoning, with gains peaking at more than 50 accuracy points in the ultra-long-CoT regime. These experiments establish HopChain as an effective, scalable framework for synthesizing multi-hop data that improves generalizable vision-language reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17024
PDF
-
Fanar 2.0: Arabic Generative AI Stack
2026-03-17 11:35:21FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad, Minhaj Ahmad, Abdulaziz Al-Homaid, Anas Al-Nuaimi, Enes Altinisik, Ehsaneddin Asgari, Sanjay Chawla, Shammur Chowdhury, Fahim Dalvi, Kareem Darwish, Nadir Durrani, Mohamed Elfeky, Ahmed Elmagarmid, Mohamed Eltabakh, Asim Ersoy, Masoomali Fatehkia, Mohammed Qusay Hashim, Majd Hawasly, Mohamed Hefeeda, Mus'ab Husaini, Keivin Isufaj, Soon-Gyo Jung, Houssam Lachemat, Ji Kim Lucas, Abubakr Mohamed, Tasnim Mohiuddin, Basel Mousi, Hamdy Mubarak, Ahmad Musleh, Mourad Ouzzani, Amin Sadeghi, Husrev Taha Sencar, Mohammed Shinoy, Omar Sinan, Yifan ZhangAbstract
We present Fanar 2.0, the second generation of Qatar's Arabic-centric Generative AI platform. Sovereignty is a first-class design principle: every component, from data pipelines to deployment infrastructure, was designed and operated entirely at QCRI, Hamad Bin Khalifa University. Fanar 2.0 is a story of resource-constrained excellence: the effort ran on 256 NVIDIA H100 GPUs, with Arabic having only ~0.5% of web data despite 400 million native speakers. Fanar 2.0 adopts a disciplined strategy of data quality over quantity, targeted continual pre-training, and model merging to achieve substantial gains within these constraints. At the core is Fanar-27B, continually pre-trained from a Gemma-3-27B backbone on a curated corpus of 120 billion high-quality tokens across three data recipes. Despite using 8x fewer pre-training tokens than Fanar 1.0, it delivers substantial benchmark improvements: Arabic knowledge (+9.1 pts), language (+7.3 pts), dialects (+3.5 pts), and English capability (+7.6 pts). Beyond the core LLM, Fanar 2.0 introduces a rich stack of new capabilities. FanarGuard is a state-of-the-art 4B bilingual moderation filter for Arabic safety and cultural alignment. The speech family Aura gains a long-form ASR model for hours-long audio. Oryx vision family adds Arabic-aware image and video understanding alongside culturally grounded image generation. An agentic tool-calling framework enables multi-step workflows. Fanar-Sadiq utilizes a multi-agent architecture for Islamic content. Fanar-Diwan provides classical Arabic poetry generation. FanarShaheen delivers LLM-powered bilingual translation. A redesigned multi-layer orchestrator coordinates all components through intent-aware routing and defense-in-depth safety validation. Taken together, Fanar 2.0 demonstrates that sovereign, resource-constrained AI development can produce systems competitive with those built at far greater scale.
Abstract (translated)
URL
https://arxiv.org/abs/2603.16397
PDF
-
CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization
2026-03-17 09:00:32Liangbin Huang, Xiaohua Liao, Chaoqun Cui, Shijing Wang, Zhaolong Huang, Yanlong Du, Wenji MaoAbstract
Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic conditions are relatively clean. To explore open-world speaker diarization, we extend this task to the visual media domain, encompassing complex audiovisual programs such as films and TV series. This new setting introduces several challenges, including long-form video understanding, a large number of speakers, cross-modal asynchrony between audio and visual cues, and uncontrolled in-the-wild variability. To address these challenges, we propose Cinematic Speaker Registration & Diarization (CineSRD), a unified multimodal framework that leverages visual, acoustic, and linguistic cues from video, speech, and subtitles for speaker annotation. CineSRD first performs visual anchor clustering to register initial speakers and then integrates an audio language model for speaker turn detection, refining annotations and supplementing unregistered off-screen speakers. Furthermore, we construct and release a dedicated speaker diarization benchmark for visual media that includes Chinese and English programs. Experimental results demonstrate that CineSRD achieves superior performance on the proposed benchmark and competitive results on conventional datasets, validating its robustness and generalizability in open-world visual media settings.
Abstract (translated)
URL
https://arxiv.org/abs/2603.16966
PDF
-
GATS: Gaussian Aware Temporal Scaling Transformer for Invariant 4D Spatio-Temporal Point Cloud Representation
2026-03-17 06:18:27Jiayi Tian, Jiaze WangAbstract
Understanding 4D point cloud videos is essential for enabling intelligent agents to perceive dynamic environments. However, temporal scale bias across varying frame rates and distributional uncertainty in irregular point clouds make it highly challenging to design a unified and robust 4D backbone. Existing CNN or Transformer based methods are constrained either by limited receptive fields or by quadratic computational complexity, while neglecting these implicit distortions. To address this problem, we propose a novel dual invariant framework, termed \textbf{Gaussian Aware Temporal Scaling (GATS)}, which explicitly resolves both distributional inconsistencies and temporal. The proposed \emph{Uncertainty Guided Gaussian Convolution (UGGC)} incorporates local Gaussian statistics and uncertainty aware gating into point convolution, thereby achieving robust neighborhood aggregation under density variation, noise, and occlusion. In parallel, the \emph{Temporal Scaling Attention (TSA)} introduces a learnable scaling factor to normalize temporal distances, ensuring frame partition invariance and consistent velocity estimation across different frame rates. These two modules are complementary: temporal scaling normalizes time intervals prior to Gaussian estimation, while Gaussian modeling enhances robustness to irregular distributions. Our experiments on mainstream benchmarks MSR-Action3D (\textbf{+6.62\%} accuracy), NTU RGBD (\textbf{+1.4\%} accuracy), and Synthia4D (\textbf{+1.8\%} mIoU) demonstrate significant performance gains, offering a more efficient and principled paradigm for invariant 4D point cloud video understanding with superior accuracy, robustness, and scalability compared to Transformer based counterparts.
Abstract (translated)
URL
https://arxiv.org/abs/2603.16154
PDF
-
RieMind: Geometry-Grounded Spatial Agent for Scene Understanding
2026-03-16 15:02:24Fernando Ropero, Erkin Turkoz, Daniel Matos, Junqing Du, Antonio Ruiz, Yanfeng Zhang, Lu Liu, Mingwei Sun, Yongliang WangAbstract
Visual Language Models (VLMs) have increasingly become the main paradigm for understanding indoor scenes, but they still struggle with metric and spatial reasoning. Current approaches rely on end-to-end video understanding or large-scale spatial question answering fine-tuning, inherently coupling perception and reasoning. In this paper, we investigate whether decoupling perception and reasoning leads to improved spatial reasoning. We propose an agentic framework for static 3D indoor scene reasoning that grounds an LLM in an explicit 3D scene graph (3DSG). Rather than ingesting videos directly, each scene is represented as a persistent 3DSG constructed by a dedicated perception module. To isolate reasoning performance, we instantiate the 3DSG from ground-truth annotations. The agent interacts with the scene exclusively through structured geometric tools that expose fundamental properties such as object dimensions, distances, poses, and spatial relationships. The results we obtain on the static split of VSI-Bench provide an upper bound under ideal perceptual conditions on the spatial reasoning performance, and we find that it is significantly higher than previous works, by up to 16\%, without task specific fine-tuning. Compared to base VLMs, our agentic variant achieves significantly better performance, with average improvements between 33\% to 50\%. These findings indicate that explicit geometric grounding substantially improves spatial reasoning performance, and suggest that structured representations offer a compelling alternative to purely end-to-end visual reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2603.15386
PDF
-
Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding
2026-03-16 12:01:58Sosuke Yamao, Natsuki Miyahara, Yuankai Qi, Shun TakeuchiAbstract
In the context of long-term video understanding with large multimodal models, many frameworks have been proposed. Although transformer-based visual compressors and memory-augmented approaches are often used to process long videos, they usually compress each frame independently and therefore fail to achieve strong performance on tasks that require understanding complete events, such as temporal ordering tasks in MLVU and VNBench. This motivates us to rethink the conventional one-way scheme from perception to memory, and instead establish a feedbackdriven process in which past visual contexts stored in the context memory can benefit ongoing perception. To this end, we propose Question-guided Visual Compression with Memory Feedback (QViC-MF), a framework for long-term video understanding. At its core is a Question-guided Multimodal Selective Attention (QMSA), which learns to preserve visual information related to the given question from both the current clip and the past related frames from the memory. The compressor and memory feedback work iteratively for each clip of the entire video. This simple yet effective design yields large performance gains on longterm video understanding tasks. Extensive experiments show that our method achieves significant improvement over current state-of-the-art methods by 6.1% on MLVU test, 8.3% on LVBench, 18.3% on VNBench Long, and 3.7% on VideoMME Long. The code will be released publicly.
Abstract (translated)
URL
https://arxiv.org/abs/2603.15167
PDF
-
Clue Matters: Leveraging Latent Visual Clues to Empower Video Reasoning
2026-03-16 09:15:12Kaixin zhang, Xiaohe Li, Jiahao Li, Haohua Wu, Xinyu Zhao, Zide Fan, Lei WangAbstract
Multi-modal Large Language Models (MLLMs) have significantly advanced video reasoning, yet Video Question Answering (VideoQA) remains challenging due to its demand for temporal causal reasoning and evidence-grounded answer generation. Prevailing end-to-end MLLM frameworks lack explicit structured reasoning between visual perception and answer derivation, causing severe hallucinations and poor interpretability. Existing methods also fail to address three core gaps: faithful visual clue extraction, utility-aware clue filtering, and end-to-end clue-answer alignment. Inspired by hierarchical human visual cognition, we propose ClueNet, a clue-aware video reasoning framework with a two-stage supervised fine-tuning paradigm without extensive base model modifications. Decoupled supervision aligns clue extraction and chain-based reasoning, while inference supervision with an adaptive clue filter refines high-order reasoning, alongside lightweight modules for efficient inference. Experiments on NExT-QA, STAR, and MVBench show that ClueNet outperforms state-of-the-art methods by $\ge$ 1.1%, with superior generalization, hallucination mitigation, inference efficiency, and cross-backbone compatibility. This work bridges the perception-to-generation gap in MLLM video understanding, providing an interpretable, faithful reasoning paradigm for high-stakes VideoQA applications.
Abstract (translated)
URL
https://arxiv.org/abs/2603.15008
PDF
-
Edit2Interp: Adapting Image Foundation Models from Spatial Editing to Video Frame Interpolation with Few-Shot Learning
2026-03-16 09:07:25Nasrin Rahimi, M{\i}sra Yavuz, Burak Can Biner, Yunus Bilge Kurt, Ahmet Rasim Emirda\u{g}{\i}, S\"uleyman Aslan, G\"orkay Aydemir, M. Ak{\i}n Y{\i}lmaz, A. Murat TekalpAbstract
Pre-trained image editing models exhibit strong spatial reasoning and object-aware transformation capabilities acquired from billions of image-text pairs, yet they possess no explicit temporal modeling. This paper demonstrates that these spatial priors can be repurposed to unlock temporal synthesis capabilities through minimal adaptation - without introducing any video-specific architecture or motion estimation modules. We show that a large image editing model (Qwen-Image-Edit), originally designed solely for static instruction-based edits, can be adapted for Video Frame Interpolation (VFI) using only 64-256 training samples via Low-Rank Adaptation (LoRA). Our core contribution is revealing that the model's inherent understanding of "how objects transform" in static scenes contains latent temporal reasoning that can be activated through few-shot fine-tuning. While the baseline model completely fails at producing coherent intermediate frames, our parameter-efficient adaptation successfully unlocks its interpolation capability. Rather than competing with task-specific VFI methods trained from scratch on massive datasets, our work establishes that foundation image editing models possess untapped potential for temporal tasks, offering a data-efficient pathway for video synthesis in resource-constrained scenarios. This bridges the gap between image manipulation and video understanding, suggesting that spatial and temporal reasoning may be more intertwined in foundation models than previously recognized
Abstract (translated)
URL
https://arxiv.org/abs/2603.15003
PDF
-
A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding
2026-03-16 02:09:48Yue Zhang, Liqiang Jing, Jia Li, Yapeng Tian, Xinya Du, Yunhui Guo, Vibhav GogateAbstract
Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos remains limited. Existing approaches typically concatenate multiple videos into a single input and perform direct inference, which introduces training-inference mismatch, information loss from frame compression, and a lack of explicit cross-video coordination. Meanwhile, current multi-video benchmarks primarily emphasize event-level comparison, leaving identity-level matching, fine-grained discrimination, and structured multi-step reasoning underexplored. To address these gaps, we introduce MVX-Bench, a Multi-Video Cross-Dimension Benchmark that reformulates 11 classical computer vision tasks into a unified multi-video question-answering framework, comprising 1,442 questions over 4,255 videos from diverse real-world datasets. We further propose SAMA, a Skill-Augmented Agentic Framework for Multi-Video Understanding, which integrates visual tools, task-specific skills, and a conflict-aware verification mechanism to enable iterative and structured reasoning. Experimental results show that SAMA outperforms strong open-source baselines and GPT on MVX-Bench, and ablations validate the effectiveness of skill design and conflict resolution.
Abstract (translated)
URL
https://arxiv.org/abs/2603.14733
PDF
-
VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting
2026-03-15 23:32:02Daeun Lee, Shoubin Yu, Yue Zhang, Mohit BansalAbstract
Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still struggles to achieve reliable spatio-temporal grounding during the reasoning process. Moreover, improving grounding typically relies on scaled training data or inference-time perception tools, which increases annotation cost or computational cost. To address this challenge, we propose VisonCoach, an input-adaptive RL framework that improves spatio-temporal grounding through visual prompting as training-time guidance. During RL training, visual prompts are selectively applied to challenging inputs to amplify question-relevant evidence and suppress distractors. The model then internalizes these improvements through self-distillation, enabling grounded reasoning directly on raw videos without visual prompting at inference. VisonCoach consists of two components: (1) Visual Prompt Selector, which predicts appropriate prompt types conditioned on the video and question, and (2) Spatio-Temporal Reasoner, optimized with RL under visual prompt guidance and object-aware grounding rewards that enforce object identity consistency and multi-region bounding-box overlap. Extensive experiments demonstrate that VisonCoach achieves state-of-the-art performance under comparable settings, across diverse video reasoning, video understanding, and temporal grounding benchmarks (V-STAR, VideoMME, World-Sense, VideoMMMU, PerceptionTest, and Charades-STA), while maintaining a single efficient inference pathway without external tools. Our results show that visual prompting during training improves grounded video reasoning, while self-distillation enables the model to internalize this ability without requiring prompts at inference time.
Abstract (translated)
URL
https://arxiv.org/abs/2603.14659
PDF
-
Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence
2026-03-13 15:40:42Seunghwan Bang, Hwanjun SongAbstract
The growing interest in embodied agents increases the demand for spatiotemporal video understanding, yet existing benchmarks largely emphasize extractive reasoning, where answers can be explicitly presented within spatiotemporal events. It remains unclear whether multimodal large language models can instead perform abstractive spatiotemporal reasoning, which requires integrating observations over time, combining dispersed cues, and inferring implicit spatial and contextual structure. To address this gap, we formalize abstractive spatiotemporal reasoning from videos by introducing a structured evaluation taxonomy that systematically targets its core dimensions and construct a controllable, scenario-driven synthetic egocentric video dataset tailored to evaluate abstractive spatiotemporal reasoning capabilities, spanning object-, room-, and floor-plan-level scenarios. Based on this framework, we present VAEX-BENCH, a benchmark comprising five abstractive reasoning tasks together with their extractive counterparts. Our extensive experiments compare the performance of state-of-the-art MLLMs under extractive and abstractive settings, exposing their limitations on abstractive tasks and providing a fine-grained analysis of the underlying bottlenecks. The dataset will be released soon.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13091
PDF
