Video_Caption
-
FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
2026-05-26 17:01:10Xintong Hu, Xuhong Huang, Jinyu Zhang, Yutong Yao, Yuchong Sun, Qiuyue Wang, Mingsheng Li, Sicheng Xie, Yitao Liu, Junhao Chen, Yixuan Chen, Yingming Zheng, Shuai Bai, Tao YuAbstract
Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tasks should be executed. However, existing robot datasets usually pair trajectories with coarse goal-level language, leaving execution-critical details such as active arm, approach direction, and contact region unspecified. This limits steerable policy learning and robotic video understanding. We introduce FineVLA, an open framework for action-aligned fine-grained VLA supervision. The framework includes: (1) a data construction tool that unifies 972,247 trajectories across 85K tasks from 10 open-source robot datasets and builds FineVLA-Data, a human-verified dataset of 47,159 fine-grained trajectories; (2) a held-out benchmark with 500 videos, 10,816 atomic facts, and 1,030 VQA questions; (3) a robotics-specialized VLM annotator for scalable fine-grained annotation; and (4) a steerable VLA policy trained with controlled mixtures of fine-grained and raw goal-level instructions. Our experiments yield three findings. First, fine-grained supervision does not sacrifice goal-level success: FG-only improves over Raw-only by +1.4 to +8.1 success-rate points across settings. Second, fine-grained and raw instructions are complementary, following a consistent inverted-U trend peaking at FG:Raw = 1:2 to 1:1. The best mixed setting reaches 86.8%/82.5% in RoboTwin simulation and 62.7/100 in real-world dual-arm manipulation (vs. 49.9 Raw-only). Third, fine-grained supervision improves steerable control: the largest real-world gains appear on pose (+23), color (+18), and approach direction (+18)--factors where goal-level instructions provide no guidance. Overall, fine-grained language should augment goal-level instructions: specifying how to execute alongside what to achieve. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2605.27284
PDF
-
Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models
2026-05-26 14:41:05Oscar Chew, Serhii Honcharenko, Qian-Hui Chen, Patricia Lu, Dishant Zaveri, Khoa D. Doan, Kuan-Hao HuangAbstract
A key capability for video understanding is reliably linking subjects to events across time, yet whether Video Large Language Models (VideoLLMs) actually achieve this remains unclear. In this work, we introduce DistractionBench to evaluate whether VideoLLMs can robustly link subjects and events in the presence of unrelated video segments. Through controlled interventions, such as inserting short advertisement clips into longer videos, we show that VideoLLMs frequently hallucinate interactions between entities from different segments, incorrectly attributing actions from injected advertisements to subjects in the main video. We characterize this systematic hallucination as bag-of-events (BoE) behavior, where models process videos as collections of events rather than temporally structured sequences. Evaluating 11 popular VideoLLMs, we find that all models exhibit substantial BoE behavior. Our findings suggest that VideoLLMs lack reliable mechanisms for temporal grounding and motivate the development of models with more robust subject-event association.
Abstract (translated)
URL
https://arxiv.org/abs/2605.27101
PDF
-
CodecCap: High-Fidelity Codec-Inspired Residual Modeling for Dense Video Captioning
2026-05-26 12:53:55Zihan Lin, Songhe Deng, Shuwei He, Danxiang Zhu, Dan Zhang, Yishu Lei, Xianlong Luo, Shikun Feng, Rui LiuAbstract
Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, whereas segment-wise captions improve coverage but introduce heavy redundancy. We propose CodecCap, a codec-inspired framework for high-fidelity dense video captioning. Analogous to video codecs, CodecCap represents videos using keyframe and residual captions. Keyframe captions exhaustively encode stable visual context, while residual captions capture temporally only localized actions, motions and changes. This effectively preserves fine-grained visual evidence while reducing redundant descriptions. To quantify the fidelity of captions, we introduce VidCapQA, a caption-then-QA benchmark with 1,000 questions across 14 capability dimensions. Results on VidCapQA show that captions directly generated by strong VLMs still miss many visual details, highlighting caption representation as a critical bottleneck. Experiments show that CodecCap significantly surpasses direct captioning with the same underlying VLMs, suggesting keyframe-residual captioning a way for high-fidelity video-language supervision. We further use CodecCap to construct CodecVDC-100K, a large-scale dense captioning dataset with anchor, residual, scene-level, and video-level supervision.
Abstract (translated)
URL
https://arxiv.org/abs/2605.26967
PDF
-
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
2026-05-26 08:16:16Peng Zhang, Guanghao Zhang, Wanggui He, Longxiang Zhang, Mushui Liu, Yan Xia, Zhenhao Peng, Weilong Dai, Jinlong Liu, Haobing Tang, Le Zhang, Hao Jiang, Pipei HuangAbstract
Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps remain in existing thinking-with-video systems. (i) Sampling density is not a learnable decision: existing methods may let the model decide where to look, but the per-window frame rate is largely fixed. As a result, fine-grained evidence is often recovered through repeated retrieval calls, which increases inference context length and training difficulty. (ii) Retrieval and answer generation are usually optimized with a single trajectory-level advantage, so the "where to look" tokens and the "how to answer" tokens receive the same credit even when one is correct and the other is not. To address these gaps, we present DynFrame, a framework that emits the temporal window and the sampling density as native tokens within a single autoregressive pass. This learnable span-density retrieval enables acquiring multi-granularity evidence with a single retrieval step. Based on the above tokenized retrieval interface, we further introduce Segment-Decoupled GRPO (SD-GRPO), which splits each rollout at the retrieval boundary and assigns role-specific token-level advantages, separately crediting the sampling decision and the answer. Trained on the curated DM-CoT-74k and DM-RL-45k, DynFrame-4B is competitive with strong 7B-8B baselines across six benchmarks (NExT-GQA, Charades-STA, ActivityNet-MR, Video-MME, MLVU, LVBench), and DynFrame-8B sets new state-of-the-art on most metrics. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.26680
PDF
-
O-MARC: Omni Memory-Augmented Compression Distillation for Efficient Video Understanding
2026-05-26 06:07:11Peiran Wu, Yunze Liu, Chi-Hao Wu, Chen Chen, Junxiao ShenAbstract
Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks do not fully isolate audio visual association in noisy user generated videos. We introduce UGC-AVQA, a public UGC benchmark with 1,000 videos and 4,816 QA pairs, where an audio removal test ensures that benchmark questions require both acoustic and visual evidence. To reduce inference cost, we propose OMAC, a training free plug in compression method that preserves salient visual memory and temporally grounded audio anchors. To further make compact models robust to compressed inputs, we introduce O-MARC, a compression distillation framework for learning with memory compressed multimodal contexts. On Qwen2.5-Omni-3B, O-MARC improves the average score across four benchmarks to 45.8, outperforming full token inference at 44.1 and OmniZip at 41.0. OMAC also keeps inference efficient, reducing latency by 34.6\% (1.53$\times$ speedup) and memory by 34.7\% compared with full token inference.
Abstract (translated)
URL
https://arxiv.org/abs/2605.26584
PDF
-
OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants
2026-05-26 02:49:47Xudong Lu, Xueying Li, Annan Wang, Yang Bo, Jinpeng Chen, Zengliang Li, Nianzu Yang, Rui Liu, Xue Yang, Jingwen Hou, Hongsheng LiAbstract
We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-visual streams. Unlike offline video understanding or text-prompted streaming QA, OmniInteract preserves the original audio-visual stream and requires models to process it online, without access to future content. User queries and ambient sounds are embedded in the audio track, requiring models to detect multimodal triggers, decide when to respond, and answer while the stream unfolds. OmniInteract contains 250 videos with 1,430 temporally grounded response slots: 1,062 1Q1A slots across real-time, proactive, and nested scenarios, and 368 1QnA slots for continuous task monitoring and step guidance. Each slot includes a trigger, response window, and target answer. We evaluate response correctness, timing, invalid outputs, interruption handling, and context continuity using Interaction-Aware Quality-Timeliness F1, Interruption Diagnostic Suite, and Nested Chain Completion Score. Experiments show that current models remain weak in streaming interaction, with the best overall IA-QTF1 reaching only 0.368 and the best 1QnA IA-QTF1 only 0.052. Further study on mathematical reasoning in full-duplex settings shows that offline capability does not necessarily transfer to online interaction. Code and datasets will be made publicly accessible at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.26485
PDF
-
Not All Modalities Are Equal: Instruction-Aware Gating for Multimodal Videos
2026-05-25 18:02:20Bonan Ding, Umair Nawaz, Ufaq Khan, Abdelrahman M. Shaker, Muhammad Haris Khan, Jiale Cao, Jin Xie, Fahad Shahbaz KhanAbstract
Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality interference, allowing irrelevant channels to distract the model. To address this issue, we present a unified multimodal video understanding framework, named UniMVU, that performs instruction-aware fusion across video, audio, depth map, or any other modality inputs via two levels of dynamic gating: inner-modality gates emphasize salient regions within each modality, whereas modality-level gates re-weight whole streams; both are conditioned on the text instruction to adaptively balance modality importance. Our UniMVU combines cross-modal self-attention with instruction-driven inner-modality gating module and a modality-level gating module with control token; for time-aligned streams we further adopt a fast-to-slow fusion scheme that reduces redundancy. Across six benchmarks (AVQA, AVSD, Music-AVQA, ScanQA, SQA3D and MVBench), our UniMVU achieves consistent gains over static-fusion baselines achieving gains as high as 13.5 in terms of CIDEr metric. Further, our analysis shows that the gating mechanism aligns with the human-interpretable modality relevance, and ablations show the contributions of inner-modality and modality-level gating. Our UniMVU provides a simple, unified recipe for instruction-aware multimodal video understanding that scales to diverse modalities without hand-crafted fusion rules.
Abstract (translated)
URL
https://arxiv.org/abs/2605.26232
PDF
-
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
2026-05-25 15:54:04Xiang An, Yin Xie, Feilong Tang, Yunyao Yan, Huajie Tan, Didi Zhu, Changrui Chen, Xiuwei Zhao, Bin Qin, Kaicheng Yang, Yifei Shen, Yuanhan Zhang, Kaichen Zhang, Wenkang Zhang, Zheng Cheng, Nansen Zhang, Chunsheng Wu, Chunjiang Ge, Zimin Ran, Dehua Song, Chunyuan Li, Shikun Feng, Ming Hu, Zhangquan Chen, Junbo Niu, Bo Li, Ziyong Feng, Ziwei Liu, Zongyuan Ge, Jiankang DengAbstract
We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of multimodal benchmarks. The model builds on a native OneVision-Encoder and incorporates Windowed Attention for efficient local computation while maintaining native resolution. Its key advance is codec-stream tokenization: it treats compressed video as a continuous bit-cost stream, where bit-cost dynamics determine adaptive temporal groups, and motion-residual cues select salient spatial evidence into compact visual canvases. This allocation concentrates a limited token budget on event-bearing content, enabling more stable long-video token compression than fixed groups of pictures. A shared 3D RoPE further places codec canvases, sampled frames, and images in a unified spatiotemporal coordinate system. Furthermore, we build the LLaVA-OV-2 data and training stack around large-scale open supervision: approximately 8M re-captioned video samples for pretraining, a 4M-sample spatial corpus for fine-tuning. We also introduce JumpScore, a temporal-localization benchmark targeting fine-grained grounding in high-frequency, densely repeated motion, a regime underrepresented by existing video evaluations. A standout capability of LLaVA-OV-2 is its unified perception across video understanding, temporal grounding, spatial grounding, and manipulation-trace reasoning. On JumpScore, LLaVA-OneVision-2-8B reaches 74.9 JumpScore mAP, surpassing Qwen3-VL-8B (30.1) by +44.8 points; under matched visual-token budgets on the same benchmark, codec-stream inputs improve temporal grounding over frame sampling by +9.7 points. Across standard benchmarks, LLaVA-OneVision-2-8B further outperforms Qwen3-VL-8B by +4.3 average points on video tasks, +5.3 on spatial tasks, and +15.6 average J&F on tracking tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2605.25979
PDF
-
StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
2026-05-25 09:23:19Ming Xie, Zizheng Huang, Xudong Tan, Chao Wang, Xiangyu Zeng, Wenxiao Wu, Tao Chen, Limin Wang, Yanwei FuAbstract
While streaming omni-video understanding demands continuous perception and proactive, real-time interaction, this crucial area remains largely under-explored. Current omni-modal methods are inherently designed for offline settings, limiting their applicability in streaming scenarios due to two fundamental flaws. First, they lack robust mechanisms to manage continuously growing audio-visual context over long horizons and cannot autonomously initiate responses at opportune moments. Second, existing benchmarks are predominantly confined to offline, single-turn question answering, failing to capture continuous, multi-turn streaming interactions. To bridge these gaps, we propose StreamOV, a novel Streaming Omni-Video understanding framework for efficient online audio-visual reasoning with bounded memory and proactive response triggering. Specifically, StreamOV introduces a multimodal evidence-guided long-short term memory that condenses historical audio-visual context into compact informative evidence under a fixed budget. It further employs a hidden-state-driven trigger to decide when to respond, avoiding explicit silence-token generation and external routers. We also curate SOVBench, the first comprehensive benchmark for online, multi-turn omni-modal evaluation. Extensive experiments show that StreamOV achieves state-of-the-art performance across diverse streaming and omni-video benchmarks, demonstrating its effectiveness for both online and offline video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2605.25621
PDF
-
UAV-OVO: Out-of-Viewpoint Generalization in UAV Action Recognition
2026-05-25 09:15:08Yu Xia, Zhengbo Zhang, Shuaihu Zhang, Zhigang TuAbstract
UAV action recognition faces a deployment shift that standard benchmarks often obscure: a model trained on UAV footage captured from low-depression viewpoints may be required to recognize the same action classes from high-depression viewpoints. While the action labels remain unchanged, this shift alters body visibility, motion projection, and scene context, encouraging models to rely on viewpoint-specific shortcuts. We introduce UAV-OVO, an Out-of-Viewpoint generalization benchmark for UAV action recognition. UAV-OVO derives view scores from uncalibrated videos, uses a view-isolation band to assign low-depression videos to the training and in-distribution test splits while reserving high-depression videos for out-of-distribution testing, and constructs ID/OOD test sets matched by class distribution so that performance differences reflect viewpoint shift rather than label imbalance. Across representative video recognizers, UAV-OVO reveals a substantial ID/OOD gap: models that fit the low-depression training distribution well often fail to transfer to held-out high-depression views, exposing viewpoint shortcuts hidden by aggregate accuracy. We further propose LATER, LoRA-Anchored Test-time Re-centering, which first adapts the recognizer with Low-Rank Adaptation (LoRA) and then uses the learned LoRA subspace as a semantic anchor for online feature re-centering. Specifically, LATER projects target-domain displacement onto the orthogonal complement of the LoRA subspace before re-centering features, reducing viewpoint-induced drift while preserving task-relevant semantics. Together, UAV-OVO and LATER provide a controlled testbed and a practical adaptation method for viewpoint-robust UAV video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2605.25615
PDF
-
MetaphorVU: Towards Metaphorical Video Understanding
2026-05-25 06:12:19Zhuoqun Li, Boxi Cao, Guiping Jiang, Fangrui Lv, Ruotong Pan, Jianan Wang, Xiangyu Wu, Hongyu Lin, Yaojie Lu, Yong Du, Ruyin Jia, Liyan, Tingting Gao, Han Li, Xianpei Han, Le SunAbstract
Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack of systematic studies on metaphorical video understanding not only constrains the real-world applicability of MLLMs but also impedes the thorough assessment of their high-order cognitive capabilities. To bridge this gap, we propose MetaphorVU-Bench, the first systematic and comprehensive benchmark dedicated to metaphorical video understanding. Through experiments, we find current MLLMs struggle with accurate metaphorical video understanding, lagging far behind human level, primarily due to defective cross-domain mapping. Motivated by this finding, we construct a metaphor knowledge graph as mapping augmentation and propose MetaphorBoost, an inference-time enhancement framework achieving consistent performance improvement. Our benchmark, analysis, and method provide useful insights and a foundation for future research on advancing MLLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2605.25461
PDF
-
FAST-ME: Foundation-aware Adaptive Stopping for Motion Estimation for Efficient IoT Video Analysis
2026-05-22 09:41:51Kakia Panagidi, Stathes HadjieftymiadisAbstract
In modern multimedia systems, efficient video processing is critical, especially in resource-constrained environments such as IoT-based camera networks, autonomous platforms, and wireless sensor multimedia systems. A key bottleneck in video compression and understanding is block motion estimation (ME), a process that remains computationally expensive despite the development of fast search techniques. This work introduces an Optimal Stopping Theory (OST) algorithm for block motion estimation based on the assessment of spatiotemporal differences within and across video frames. It also proposes a semantic-aware motion estimation framework that integrates Foundation Models (FMs) with the OST-based decision process. By leveraging pretrained visual models such as Vision Transformers (ViT) and the Segment Anything Model (SAM), the framework extracts semantic attention scores that indicate the importance of motion within specific spatial regions. These scores are fused with traditional distortion-based metrics, such as the Sum of Absolute Differences (SAD), to guide a hybrid stopping criterion that jointly considers motion magnitude and semantic relevance. The resulting adaptive algorithm stops early in redundant regions while continuing the search in areas where motion is semantically significant. Experiments compare the proposed solution with widely used approaches from the literature on benchmark and multimodal video datasets. The proposed method achieves a significant reduction in computation with minimal accuracy loss and improved semantic coverage. The results highlight the benefits of bridging low-level motion analysis with high-level semantic reasoning, offering a promising direction for efficient multimodal video understanding in next-generation smart systems.
Abstract (translated)
URL
https://arxiv.org/abs/2605.23428
PDF
-
Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization
2026-05-22 08:21:26Tianyu Wang (School of Economics and Management, Beihang University, Beijing 100191, China), Junjie Wu (School of Economics and Management, Beihang University, Beijing 100191, China, Key Laboratory of Data Intelligence and Management, Beihang University, Ministry of Industry and Information Technology, Beijing 100191, China), Jingquan Gao (School of Economics and Management, Beihang University, Beijing 100191, China), Shishuo Li (School of Economics and Management, Beihang University, Beijing 100191, China)Abstract
Temporal Action Localization (TAL) has been extensively studied in generic video understanding, while fine-grained sports scenarios, such as professional badminton, remain underexplored due to their complex and subtle spatio-temporal dynamics. In this paper, we focus on fine-grained TAL in professional badminton videos and introduce a new benchmark dataset, Fine-Badminton, which consists of 31 matches with 29 fine-grained stroke categories, covering 2104 rallies and 27597 annotated actions. To effectively capture the intricate motion patterns in such scenarios, we propose a Decoupling Spatio-Temporal Adapter (DSTA), which enables efficient modeling of spatio-temporal features within a parameter-efficient framework. Specifically, DSTA decomposes motion representation into three parallel branches, capturing temporal dynamics as well as vertical and horizontal spatial variations. The design allows the model to better distinguish subtle differences among fine-grained actions. Extensive experiments on both the Fine-Badminton dataset and the ShuttleSet benchmark demonstrate that the proposed method achieves state-of-the-art performance while introducing only a marginal increase in computational and parameter cost. These results validate the effectiveness and efficiency of the proposed approach for fine-grained temporal action localization.
Abstract (translated)
URL
https://arxiv.org/abs/2605.23355
PDF
-
VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding
2026-05-21 18:00:22Haichen He, Jiayi Zhou, Sifeng Shang, Yihan Hu, Yuanhan Zhang, Kaiyang ZhouAbstract
Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal spans within extreme video durations. Mastering this intense cognitive load constitutes the fundamental bottleneck in long video understanding. While existing benchmarks have driven progress by scaling up video duration, their evaluation tasks often require comprehending only short and isolated video segments, falling short of capturing the challenge of ultra-long-context reasoning. To measure this cognitive load, we emphasize continuous certificate length, defined as the video length a human must continuously watch to definitively answer a given question. Driven by this metric, we introduce VideoOdyssey, a benchmark specifically designed for ultra-long-context and omni-modal video understanding. VideoOdyssey is characterized by three key features: 1) Extreme video duration and diversity: spanning 11 domains and 54 subcategories with an average video duration of 109 minutes; 2) Comprehensive evaluation scenarios: offering two subsets to address different research focuses, i.e., VideoOdyssey-V for probing the limits of visual understanding in MLLMs, and VideoOdyssey-AV for evaluating synchronized audio-visual understanding for omni-modal models; 3) Ultra-long and multi-level continuous certificates: extending the average continuous certificate to 16 minutes for VideoOdyssey-V and 12.8 minutes for VideoOdyssey-AV. Crucially, we design 5 granular levels from seconds to hours, providing a comprehensive diagnostic tool to evaluate models across varying context lengths and cognitive loads. Extensive evaluations show that bottlenecks of current MLLMs extend beyond simple retrieval to include struggles with continuous reasoning across varying context lengths, fine-grained perception, and non-verbal omni-modal understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2605.22907
PDF
-
Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs
2026-05-21 17:59:56Jongseo Lee, Hyuntak Lee, Sunghun Kim, Sooa Kim, Jihoon Chung, Jinwoo ChoiAbstract
Video Large Language Models (Video-LLMs) have made rapid progress on temporal video understanding, yet many fail at a basic perceptual primitive: signed image-plane motion direction. On simple videos of a single object moving left, right, up, or down, most Video-LLMs perform near chance, with above-chance cases largely attributable to prediction biases rather than genuine direction understanding. We call this failure directional motion blindness. We localize the failure by tracing motion direction information through the Video-LLM pipeline. Motion direction remains linearly accessible from the vision encoder, projector, and LLM hidden states, but the readout fails to bind this signal to the correct verbal answer option, revealing a direction binding gap. Although synthetic motion direction instruction tuning reduces this gap on the source domain, motion direction concept vector analysis shows that visual complexity weakens the signal magnitude and limits out-of-domain generalization. We introduce MoDirect, a dataset family for motion direction instruction tuning and evaluation, and DeltaDirect, a diagnosis-driven, projector-level objective that predicts normalized 2-D motion vectors from adjacent-frame feature deltas. On MoDirect-SynBench, instruction tuning with DeltaDirect improves motion direction accuracy from 25.9% to 85.4%. On MoDirect-RealBench, DeltaDirect improves real-world motion direction accuracy by 21.9 points over the vanilla baseline without real-world tuning data, while preserving standard video-understanding performance. Code: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2605.22823
PDF
-
Cambrian-P: Pose-Grounded Video Understanding
2026-05-21 17:59:45Jihan Yang, Zifan Zhao, Xichen Pan, Shusheng Yang, Junyi Zhang, Bingyi Kang, Hu Xu, Saining XieAbstract
Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet this signal is largely absent from multimodal LLMs (MLLMs) for video understanding, which process frames as isolated 2D snapshots, instead of the persistent scene humans perceive. We revisit pose as a lightweight supervisory signal and introduce Cambrian-P, a video MLLM augmented with per-frame learnable camera tokens and a pose regression head. With a carefully designed sampling scheme, the model achieves substantial gains of 4.5-6.5% on spatial reasoning benchmarks such as VSI-Bench, generalizes across eight additional spatial and general video QA benchmarks, and, as a byproduct, achieves state of the art streaming pose estimation on ScanNet. Surprisingly, training on pseudo-annotated poses from in-the-wild video further improves general video QA benchmarks, showing pose helps beyond spatial reasoning. Together, these results position camera pose as a fundamental signal for video models that reason about the physical world.
Abstract (translated)
URL
https://arxiv.org/abs/2605.22819
PDF
-
Segment Anything with Motion, Geometry, and Semantic Adaptation for Complex Nonlinear Visual Object Tracking
2026-05-21 14:25:28Deyi Zhu, Yuji Wang, Yong Liu, Yansong Tang, Bingyao Yu, Jiwen Lu, Jie ZhouAbstract
Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects and challenging scenarios with distractors, occlusion, and nonlinear motion. Recent vision foundation models, exemplified by SAM 2, learn strong video understanding priors from large-scale pretraining and offer a promising foundation for building more robust and generalizable trackers. However, directly applying SAM 2 to VOT remains suboptimal, as it does not explicitly model target motion dynamics or enforce geometric and semantic consistency across frames, both of which are essential for reliable tracking. To address this issue, we propose SAMOSA, a new tracking framework that adapts SAM 2 to complex VOT scenarios by explicitly leveraging motion, geometry, and semantic cues. Specifically, we introduce a lightweight nonlinear motion predictor to model target dynamics and guide mask selection as well as memory filtering. We further exploit semantic cues to detect target shifts and recover from tracking failures, while geometric cues are incorporated as structural constraints to improve tracking stability. In this way, SAMOSA bridges the gap between the implicit video understanding prior of SAM 2 and explicit tracking-oriented modeling. Extensive experiments show that SAMOSA consistently outperforms state-of-the-art SAM 2--based approaches on general benchmarks, demonstrates stronger generalization than supervised VOT methods, and achieves substantial gains on anti-UAV datasets, which typify complex nonlinear motion scenarios. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.22538
PDF
-
ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs
2026-05-21 08:27:15Bingjun Luo, Tony Wang, Chaoqi Chen, Xinpeng DingAbstract
Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficiency, existing methods primarily reduce redundancy by pruning or merging tokens based on importance or similarity. However, these approaches largely overlook a critical dimension of video content, i.e., changes and turning points, and they lack a collaborative model for spatio-temporal relationships. To address this, we propose a new perspective: similarity is for identifying redundancy, while difference is for capturing key events. Based on this, we designed a training-free framework named ST-SimDiff. We first construct a spatio-temporal graph from the visual tokens to uniformly model their complex associations. Subsequently, we employ a parallel dual-selection strategy: 1) similarity-based selection uses community detection to retain representative tokens, compressing static information; 2) temporal difference-based selection precisely locates content-changing points to preserve tokens that capture key dynamic shifts. This allows it to preserve both static and dynamic content with a minimal number of tokens. Extensive experiments show our method significantly outperforms state-of-the-art approaches while substantially reducing computational costs. Our code is available in this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.22158
PDF
-
Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding
2026-05-21 07:16:45Bingjun Luo, Tony Wang, Hanqi Chen, Xinpeng DingAbstract
Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficiently compressing visual tokens while preserving spatiotemporal interactions. Existing methods, such as LLaVA family, utilize simplistic pooling or interpolation techniques that overlook the intricate dynamics of visual tokens. To bridge this gap, we propose ST-GridPool, a novel training-free visual token enhancement method designed specifically for Video LLMs. Our approach integrates Pyramid Temporal Gridding (PTG), which captures multi-grained spatiotemporal interactions through hierarchical temporal gridding, and Norm-based Spatial Pooling (NSP), which preserves high-information visual regions by leveraging the correlation between token norms and semantic richness. Extensive experiments on various benchmarks demonstrate that ST-GridPool consistently enhances performance of Video LLMs without requiring costly retraining. Our method offers an efficient and plug-and-play solution for improving visual token representations. Our code is available in this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2605.22078
PDF
-
Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
2026-05-21 04:03:25Zelin Zheng, Xinyan Liu, Ruixin Li, Antoni B. Chan, Guorong Li, Qingming Huang, Laiyun QingAbstract
Current Video-LLM approaches for Video Temporal Grounding (VTG) typically rely on direct timestamp generation from an unstructured visual-token stream, often leading to brittle numerics and inconsistent boundaries. To address this, we propose Foresee-to-Ground (F2G), a framework that reformulates VTG as a verifiable Identify-then-Measure problem. F2G integrates Predictive Temporal Perception with Evidence-Driven Reasoning: it learns boundary-sensitive temporal representations to build a video-wide evidence pool of candidate event segments, and exposes these segments to the LLM as citable evidence units that bind boundary prediction to explicit event hypotheses. By decoupling event identification from precise boundary measurement, F2G stabilizes grounding and makes predictions verifiable. Extensive experiments demonstrate that F2G consistently improves grounding accuracy across diverse benchmarks, transfers robustly across different Video-LLM backbones, and preserves general video understanding capabilities.
Abstract (translated)
URL
https://arxiv.org/abs/2605.21973
PDF
