Video_Caption
-
StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary
2026-08-20 07:19:29Chenxi Shao, Bozhong Wang, Jiaxin Huang, Zhao Liu, Sunwei Zhu, Tianxin Hang, Gaoqi He, Yang Li, Changbo WangAbstract
Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be recalled under bounded computation and memory. This challenge is pronounced in live soccer commentary, where a system must describe completed events, summarize recent play, recall earlier events, or remain silent using only information available before each utterance. We present StreamSoccer, an event-driven system that uses event memory as its intermediate representation. A fixed-budget active memory integrates the stream; completed event states are retained locally and consolidated into retrievable historical records. A unified generator uses current, recent, and historical context to produce three commentary modes, while a rule-assisted scheduler selects a mode or silence. Unlike streaming video-language models organized around frames, visual tokens, or caches, and soccer-commentary methods based on predefined clips or output timestamps, StreamSoccer explicitly models event lifecycles. We construct a three-track streaming soccer commentary dataset and a layered evaluation protocol. At common reference anchors, StreamSoccer obtains CIDEr scores of 38.62, 23.96, and 17.39 for current-event, recent-window, and historical-memory commentary, ranking first on the current-event and historical-memory tracks and second on recent-window. Controlled ablations show that local completed events improve all tracks and that the full system performs best on all three. Across 174 raw-video runs on 58 matches, per-minute RTF p95 ranges from 0.10 to 0.22 without sustained growth with match history. These results indicate that event memory supports streaming soccer commentary across temporal scopes while controlling long-history computation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.19723
PDF
-
PL-NBA: A Possession-level Universal Basketball Video Dataset Supporting Multiple Visual Understanding Tasks
2026-08-20 05:29:05Yunhao Zhao, Haoying Sun, Jiarui Li, Zhuming Wang, Ya Jing, Xiangbo Shu, Lifang Wu, Changwen ChenAbstract
Visual understanding in sports has emerged as a hot topic in computer vision in recent years. Most existing basketball video datasets adopt single action or activity as sample, which can neither preserve the temporal continuity of game events nor support complex tasks such as action anticipation. To address this issue, this paper constructs the first possession-level basketball video dataset (PL-NBA), in which each sample is composed of a complete NBA offensive possession. Collected from 60 NBA games, PL-NBA contains 11,000 valid offensive possession clips and 31,567 annotated events with player names, captions, event types and timestamps. Each video clip includes multiple events and preserves the continuity of events, which is helpful for analysis of tactic. Experiment is conducted on multiple visual understanding tasks, including event recognition, video captioning, temporal action localization and action anticipation. Experimental results show that existing methods achieve limited performance on above four tasks, demonstrating that PL-NBA is a challenging benchmark for sports video understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2608.19646
PDF
-
Vision-Language Models for Egocentric Video: From Hand-Object Interaction to Embodied AI
2026-08-19 08:21:58Mohammad Zamani, Fatemeh ZiaeetabarAbstract
Egocentric video captures activities from the wearer's perspective, providing a direct view of human attention, hand--object interaction, and goal-directed behavior. This perspective is increasingly important for wearable intelligence, assistive systems, human--robot interaction, and embodied AI, yet it introduces challenges including ego-motion, occlusion, small active objects, viewpoint-dependent appearance, and long-range temporal dependencies. Vision--language models (VLMs) offer a promising foundation for addressing these challenges by linking visual observations with semantic knowledge and natural-language supervision. This survey presents a critical review of VLMs for egocentric video understanding, tracing the progression from conventional recognition architectures to multimodal foundation models and embodied systems. We organize the literature around tasks, datasets, hand--object interaction understanding, temporal reasoning, frame and clip selection, multimodal representation learning, prompting, semantic alignment, and model adaptation. Particular attention is given to graph-based and object-centric reasoning as mechanisms for modeling relations among hands, objects, actions, and scene context over time. We further examine how first-person perception and multimodal foundation models support wearable assistance, robot skill learning, human-to-robot transfer, and embodied decision making. Across the reviewed literature, a consistent limitation emerges: current models recognize visible objects more reliably than evolving interactions, actions, and user intent, especially over long activities. We therefore identify temporally grounded reasoning, interaction-aware supervision, efficient long-video processing, multimodal fusion, graph-enhanced representations, cross-domain generalization, privacy, and trustworthy evaluation as key priorities for deployable embodied intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2608.18671
PDF
-
StateTrace: An Object-Centric Framework for Hidden-State Spatiotemporal Reasoning in Long Videos
2026-08-19 04:31:56Yu Han, Wenhao Li, Yichao Cao, Hongyan Xu, Shuo Yang, Shan You, Xiu SuAbstract
Existing VLMs have achieved strong performance in video understanding, yet they struggle with long-video spatiotemporal reasoning when target objects become invisible, often mistaking "invisible" for "unknown". We define this challenge as hidden-state spatiotemporal reasoning: inferring object states during prolonged invisible intervals from context interactions. To address this, we propose StateTrace, a novel object-centric framework that endows VideoLLMs with an explicit mechanism for hidden state reasoning in long videos. StateTrace builds a reusable spatiotemporal state memory that organizes object trajectories, inter-object relations, and state-transition events into a structured reasoning substrate. At inference time, it retrieves question-relevant state-evolution trajectories and converts them into compact reasoning cues, enabling the model to explicitly reason about why an object disappears, how its state evolves while invisible, and whether that state should persist at query time. We further build HSR-Bench, a diagnostic benchmark for hidden-state reasoning, containing 1,427 video-QA samples from 1,384 unique videos. Extensive experiments across multiple VideoLLMs show that StateTrace consistently improves performance on both public benchmarks and HSR-Bench (e.g., improving VideoLLaMA3 from 39.6 to 64.2 on HSR-Bench).
Abstract (translated)
URL
https://arxiv.org/abs/2608.18532
PDF
-
Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment
2026-08-18 15:56:08Marko Haralovi, Zhiqi Miao, Alexander Machiel Bont, Jiapan Guo, Frans van Workum, Estefania TalaveraAbstract
Surgical performance assessment in minimally invasive surgery largely relies on manual expert review, making it time-consuming, subjective, and difficult to scale. While existing surgical video understanding methods address tasks such as instrument segmentation, surgical phase recognition, and action recognition, they do not explicitly capture fine-grained tissue handling, a key indicator of surgical quality. To address this gap, we introduce tissue tension recognition, a new clinically motivated video understanding task for laparoscopic and robot-assisted rectal cancer surgery. To support this task, we construct SurgTension, the first expert-annotated tissue tension dataset, providing a benchmark for objective tissue tension recognition. We further propose TensionTRAC, a lightweight trajectory-based framework that models tissue tension from sparse point trajectories. Using a compact trajectory encoder, TensionTRAC achieves competitive performance against strong pretrained video backbones.
Abstract (translated)
URL
https://arxiv.org/abs/2608.17935
PDF
-
Test-time Reinforcement Learning for Anomalous Video Understanding
2026-08-18 13:49:45Huining Li, Yuxiang Duan, Jiyang Tan, Qian Li, MingCai Chen, Jian Zhang, Xingdong Sheng, Yuntao DuAbstract
Anomalous video understanding aims to identify abnormal events in videos and interpret their semantic meanings beyond simple anomaly detection. Recent video large language models (Video-LLMs) have demonstrated promising zero-shot capabilities for this task, yet their performance remains limited due to insufficient adaptation to diverse anomaly patterns and evolving environments. Test-time reinforcement learning offers a promising solution by enabling models to improve through self-generated feedback signals without requiring additional human annotations. However, applying it to anomalous video understanding remains challenging due to three issues: (1) generated pseudo-labels can be unreliable when consensus is weak; (2) binary reward designs fail to capture uncertainty in model generations, resulting in ineffective optimization signals; and (3) unanimous rollout groups receive identical rewards, causing group-relative advantages to collapse and eliminating effective policy-gradient signals. To address these challenges, we present a novel test-time reinforcement learning framework for anomalous video understanding by introducing dual-query consistency filtering, an entropy-aware consensus reward, and a virtual negative anchor mechanism. The framework retains reliable samples through consistency across semantically equivalent queries, combines answer agreement with generation uncertainty for reward estimation, and introduces a virtual negative anchor to create reward variation in unanimous rollout groups, thereby preserving effective group-relative optimization signals. Experiments on VAU-Bench show that our method outperforms the compared frozen and supervised baselines. The gains are most pronounced on the ECVA subset of VAU-Bench with thinking, where accuracy improves from 75.81% to 90.00% relative to the frozen backbone.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26099
PDF
-
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
2026-08-18 05:58:40Bonan Zhang, Shiyu Dong, Quan Hung Tran, Katharina Gschwind, Shuqi Yang, Sijia Chen, Adel Ahmadyan, Seungwhan Moon, Lu Zhang, Ahmed Kirmani, Babak Damavandi, Anuj KumarAbstract
Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves performance. However, dense scaling increases compute cost and inference latency. Mixture-of-Experts (MoE) architectures offer a compelling alternative, having enabled efficient scaling in LLMs, yet the MoE design space for CLIP-style vision encoders remains underexplored at State-of-the-Art (SOTA) levels. In this work, we systematically study MoE designs for vision encoder scaling and find that fine-grained MoE topologies yield substantial gains over both dense and standard MoE counterparts. We further propose an auxiliary-loss-free balancing variant for better expert utilization, and design a specialized MoE kernel to mitigate inference latency overhead. To enhance video capabilities while preserving image knowledge, we introduce frame-level distillation paired with a novel freezing mechanism. We pretrain a series of Mixture-of-Experts Vision Encoders (MoE-ViE) across a range of sizes, all consistently outperforming their dense counterparts. Our largest model matches the zero-shot performance of a SOTA encoder 1.7x its size at 76% of its latency. When aligned with an LLM, MoE-ViE surpasses all compared encoders on image and video benchmarks, including those with up to 5x more activated parameters. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.17402
PDF
-
Sterilizable Scene Graph Generation for Operating Rooms
2026-08-17 12:06:49Nick Lemke, Ssharvien Kumar Sivakumar, Antoine P. Sanner, John Kalkhof, Henry John Krumb, Ghazal Ghazaei, Anirban MukhopadhyayAbstract
Scene graph generation from surgical video enables a holistic and structured understanding of surgical scenes by modeling objects and their semantic relationships. Despite recent advances, state-of-the-art approaches rely on large, parameter-heavy deep learning models that are impractical for deployment in the operating room (OR) due to hardware footprint, hygiene constraints, latency, and data privacy concerns. To the best of our knowledge, this is the first scene graph generation method built on NCAs and the first NCA framework capable of learning structured representations. We introduce SG-NCA, a lightweight scene graph generation framework based on Neural Cellular Automata (NCA), designed for inference in fanless devices critical for OR hygiene protocols. SG-NCA is the first scene graph generation combining NCA-based multiclass segmentation for efficient object detection and feature extraction with a lightweight relation predictor. We evaluate SG-NCA on videos of cataract surgery and cholecystectomy, demonstrating performance comparable to established baselines while requiring 55x fewer parameters. We showcase deployment on fanless edge devices better suited for the OR and demonstrate downstream applications such as surgical video captioning, highlighting SG-NCA's potential for affordable, privacy-preserving, and OR-ready intraoperative scene understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16469
PDF
-
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding
2026-08-17 09:25:36Keming Wu, Baoyi Wang, Kaichen Zhang, Xiang An, Zuhao Yang, Sudong Wang, Haowei Zhu, Tingxuan Huang, Hongcheng Gao, Bin WangAbstract
Streaming video understanding demands direct responses from the causally observed prefix of an unfolding video. Existing systems add inference-time memory, retrieval, and compression, yet a training-free sliding-window baseline already matches them. We therefore fix a memory-free recent-window protocol and ask how far post-training alone can go. Reinforcement learning with verifiable rewards fits this regime poorly, encouraging long ``think-then-answer'' generations, while on-policy distillation (OPD) supplies dense token-level teacher supervision on student trajectories but is stable only when both models train in thinking mode. These observations lead to \textsc{StreamOPD}, a recipe combining verifiable streaming-video data, thinking-mode OPD, and instruct-mode deployment. It raises StreamingBench from $77.9\%$ to $83.9\%$---within $0.3$ points of the 9B teacher---and improves OVO-Bench excluding its hallucination-detection subtask (HLD) by $9.1$ points under unchanged inference. As a teacher-privilege extension, \emph{Spatio-Temporal CueGate (ST-CueGate)} aggregates cue-versus-no-cue teacher likelihood ratios into a group-relative response score that reweights OPD. It reaches $71.9\%$ on OVO-Bench (excluding HLD) and $64.9\%$ on Video-MME, and is the only variant that stays above the base model on all four benchmarks. Replacing the teacher with a frozen copy of the student's initial policy---on-policy self-distillation---retains most of these gains and lifts HLD to $57.0\%$, above both the untrained student and the 9B teacher, so abstention loss is not intrinsic to the recipe. We provide a transparent and reproducible reference for open-source streaming-video research.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16320
PDF
-
Audio-Visual Segmentation via Depth-Guided Collaborative Modeling
2026-08-17 08:55:15Zhaojin Fu, Yuyang Hong, Qi Yang, Zili Wang, Kun Ding, Shiming Xiang, Bin FanAbstract
Audio-Visual Segmentation (AVS) is a fundamental task in multimodal perception that performs pixel-level segmentation of sounding objects in videos by leveraging both visual and audio cues. It has broad applications in video understanding, human-computer interaction, and autonomous driving. However, most existing AVS methods do not explicitly model geometric cues such as relative distance and occlusion, thereby limiting the robustness of cross-modal alignment. In human perception, spatial structure is naturally integrated with audio-visual evidence to accurately localize sounding objects. Motivated by this, we incorporate estimated depth as a spatial structural cue for AVS and propose DGCM-AVS, a tri-modal framework that jointly models audio, visual, and depth information. Specifically, we design a Depth-Aware Dynamic Modulator to improve the separation of adjacent objects while preserving intra-object feature consistency. Furthermore, we propose Depth-Guided Progressive Fusion, which uses depth as an intermediate bridge to progressively align audio cues with visual features. Compared to state-of-the-art methods, DGCM-AVS achieves relative improvements of 10.2 percent in M_J and 8.7 percent in M_F on the AVSS dataset. We believe our study highlights depth as a promising yet underexplored modality for AVS and may encourage further research in this direction.
Abstract (translated)
URL
https://arxiv.org/abs/2608.16285
PDF
-
EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input
2026-08-16 08:28:01Matteo Stoiber, Niels Buus LassenAbstract
The use of multimodal LLMs (MLLMs) for egocentric video understanding with wearable devices is constrained by the token budget. Memory and compute cost scale with the number of visual tokens, and high-resolution video quickly becomes expensive to transmit and process at scale. Prior work (GazeLLM) addresses this by cropping the video around the camera wearer's gaze. This reduces the number of visual tokens by about tenfold while maintaining or improving the quality of full-resolution descriptions. However, this compression strategy depends on dedicated eye-tracking hardware, which is unavailable on consumer smart glasses. Building a software-only substitute poses a joint constraint: the predictor must be accurate enough to preserve downstream description quality, yet light enough to run on-device, within the power and compute budget of a smartphone. We address this with EgoGazeLite, a lightweight dual-process gaze predictor for egocentric video. Across two MLLMs, three automated metrics, and two LLM judges, predicted-gaze crops show no significant difference from ground-truth-gaze crops. Equivalence is confirmed in all ten cases. EgoGazeLite achieves this at 15.7M parameters, 6.71 GFLOPs, and runs the full gaze-and-crop pipeline end-to-end in real time (21.6 ms/frame) on consumer accelerator hardware. Together, these results remove the need for eye-tracking hardware for token-efficient, gaze-conditioned egocentric video understanding with MLLMs.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15614
PDF
-
CrossView: Can Vision-Language Models Reason Across Cameras?
2026-08-16 05:25:04Sahil Shah, S P Sharan, Harsh Goel, Manvik Pasula, Adithya Hebbalae, Minkyu Choi, Sandeep P. ChinchaliAbstract
Video understanding benchmarks have long centered on single-camera settings, where modern multi-modal language models achieve strong performance across image and video tasks. Yet, the real world runs on multi-camera networks: autonomous vehicles, security systems, and robots all gather data across many simultaneous views. We argue that this is not simply "more" of the single-camera problem; it is fundamentally different. Multi-camera reasoning requires handling context that scales with the number of views, resolving occlusions visible from only a subset of cameras, judging which views matter, and integrating evidence across perspectives that may overlap or diverge. Current models struggle with exactly these challenges, yet no benchmark systematically targets them. We introduce CrossView, a multi-camera video question-answering benchmark spanning autonomous driving, security surveillance, egocentric/exocentric video, and robotics. Evaluation of proprietary models, such as GPT-5.2, and open-source models, like Qwen3-VL, reveals consistently low accuracy, with open-source models trailing by a wide margin. Performance scales strongly with a model's ability to jointly process multiple viewpoints, positioning CrossView as a rigorous benchmark for multi-camera video. We open-source our code and dataset at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15539
PDF
-
Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition
2026-08-14 19:50:31Chengyan Wang, Hanliang Xie, Yueyi Yang, Haoyu ChenAbstract
While Multimodal Large Language Models (MLLMs) excel in general video understanding, their capability in fine-grained and motion-centric tasks remains limited. This limitation is particularly critical in micro-gesture recognition (MGR), where micro-gestures (MGs) - subtle, short-duration, and spatially localized human movements - serve as key discriminative signals for implicit affective analysis, yet are easily neglected following common prompting practices. Although MGR has been intensively studied by many discriminative approaches, the use of MLLMs for MGR is underexplored, with notably poor performance. We hypothesize that the motion-sensitive representation ability of MLLMs is constrained by their inherent single-pass forward inference, which can be substantially enhanced through carefully designed test-time guidance. Motivated by this, building on our prior findings regarding temporal insensitivity in Video LLMs, we diagnose zero-shot MGR errors in the Negative Log-Likelihood (NLL) space. We observe that MLLMs suffer from two bottlenecks: 1) insufficient localized evidence and 2) severe score biases driven by language and motion-agnostic appearances. Thus, we propose a novel test-time evidence calibration framework that improves both reasoning details and prediction reliability. Specifically, we introduce a tree search mechanism to progressively acquire localized, fine-grained visual evidence, coupled with a test-time calibration module to mitigate score biases. The multi-cue fusion module then integrates evidence from multiple cues without relying on a single cue for final prediction. Our framework achieves mean-class accuracies of 26.84\% on iMiGUE and 22.10\% on MA-52, significantly outperforming the Qwen2.5-VL baseline, which produces 16.15\% and 10.20\%, respectively. The code will be available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14854
PDF
-
OvDSGG: End-to-End Open-Vocabulary Dynamic Scene Graph Generation
2026-08-14 19:12:40John Helsby, Yi Yang, Bodo Rosenhahn, Michael Ying YangAbstract
Dynamic scene graphs (DSGs) capture spatio-temporal interactions across videos as $\langle$subject, predicate, object$\rangle$ triplets, and underpin downstream tasks such as video captioning, video question answering, and action analysis. However, end-to-end dynamic scene graph generation (DSGG) methods are closed-set: they recognize only objects and predicates from a fixed training vocabulary and struggle with the long-tailed distribution of rare concepts, severely limiting their real-world applicability. Existing open-vocabulary models typically inherit pretrained large language models, resulting in multi-stage training and inference with substantial cost. We introduce OvDSGG, the first end-to-end framework for open-vocabulary DSGG. OvDSGG builds on top of an open-vocabulary Spatial Backbone and a Temporal Backbone; we further propose a Triplet Feature Extraction Module that bridges them, and a Visual-Language Alignment Module that preserves open-vocabulary recognition by learning an adaptive decision boundary in the joint visual-language feature space, without expensive knowledge distillation in existing methods. We further introduce a rigorous open-vocabulary DSGG benchmark adapted from Action Genome, with disjoint Base/Novel splits for both objects and predicates. OvDSGG significantly outperforms open-vocabulary baselines across all metrics, with zero-shot Recall@$K$ scores 10.0--20.4 percentage point higher than the next-best baseline, while on closed-set DSGG remaining competitive with state-of-the-art models. Code and benchmark are publicly available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14835
PDF
-
On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos
2026-08-14 12:37:48Darakshan Rashid, Raza Imam, Ufaq Khan, Muhammad Bilal, Shazad Ashraf, Dwarikanath Mahapatra, Mohammad Yaqub, Muhammad Haris Khan, Imran Razzak, Brejesh Lall, Lena Maier-Hein, Yutong XieAbstract
Temporal vision-language models (TVLMs) offer a reusable, prompt-based interface for surgical video understanding, yet, their robustness under clinically realistic acquisition artifacts in endoscopy remains insufficiently characterized. In practice, degradations such as defocus, haze, motion blur, noise, cautery smoke, and packet loss introduce structured distribution shifts which may compromise video-text alignment. We study the robustness of temporal VLMs under such shifts caused by corruptions in clip frames. We introduce Endo-C6, a compact corruption benchmark of six endoscopy-realistic perturbations evaluated at a fixed high severity, and apply it to public Gastrointestinal (GI) endoscopy and laparoscopic cholecystectomy videos. Under a standardized prompt protocol, we benchmark 3 recent surgical TVLM baselines and analyze robustness in both mean and worst-case settings, spanning 294 dataset-level evaluations. Finally, we present RobustEndoCLIP, obtained by few-shot parameter-efficient tuning with VeRA, outperforming existing TVLM baselines. Our findings show that off-the-shelf TVLMs can exhibit severe worst-case collapse under endoscopy-specific corruptions, whereas lightweight few-shot adaptation can substantially improve corrupted performance and robustness without changing the prompt-based interface. We expect Endo-C6 to support standardized robustness reporting and promote more reliable clinical vision-language systems.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14262
PDF
-
NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video
2026-08-13 13:13:43Yuheng Huang, Jianlang Chen, Jiayang Song, Hua Qi, Aza Kai, Vincent Markert, Edison Marrese-Taylor, Jianjun Zhao, Lei MaAbstract
Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain implicit. However, existing benchmarks rarely evaluate these capabilities jointly, particularly in high-context, non-English media. To address this gap, we introduce NARU, a benchmark designed to evaluate Narrative evolution and Reasoning on cultural Understanding in Japanese long-form video. NARU consists of 1,481 questions grounded in 155 videos totaling 146.8 hours, spanning four narrative and five cultural dimensions. To construct the benchmark at this scale, we propose a hierarchical memory-based annotation pipeline that transforms raw video into structured event, narrative, and cultural annotations, then generates questions via task-oriented synthesis and iterative shortcut removal. The construction process includes two native-speaker verification stages involving 68 annotators. Evaluations across eight model configurations reveal substantial limitations in both long-range narrative integration and culturally grounded reasoning. By exposing these persistent gaps, NARU offers a systematic testing ground for developing MLLMs capable of reliably interpreting long-form, high-context video.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13210
PDF
-
A Controlled Study of Self-Supervised Image and Video Pretraining under Limited Resources
2026-08-13 12:47:36Brun\'o B. Englert, Gijs DubbelmanAbstract
Visual foundation models are a cornerstone of image and video understanding but typically require large amounts of data and computation. The current scale required for pretraining visual foundation models may be unsustainable or unnecessary, and significant benefits arise when effective models can be obtained with fewer resources. To better understand how self-supervised learning (SSL) objectives behave under resource constraints, we conduct a controlled study of image and video SSL objectives under matched data, architecture, and compute budgets. We compare contrastive, reconstruction, feature-prediction, and diffusion objectives and evaluate both standalone and jointly trained image-video SSL formulations across a diverse set of image and video understanding tasks. Our results show that DINOv2-style pretraining consistently provides the strongest overall performance under limited resources. Furthermore, combining DINOv2 with video SSL objectives such as VideoMAE substantially improves image classification and segmentation performance, but degrades video tracking and camera-pose estimation performance, revealing an important tradeoff between semantic and geometric representation learning. These findings suggest that combining image and video SSL objectives can be beneficial in resource-limited settings, while highlighting the need for improved methods that better balance semantic, temporal, and geometric supervision.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13183
PDF
-
EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory
2026-08-13 11:40:56Weitao Chen, Hu Jiaxin, Xie Tianyidan, Yang Li, Yuyi Qian, Banghao Xu, Ziheng Tang, Shenyi Wang, Mingyue Yu, Duo Li, Jiacheng Shi, Gao Wang, Zhan Xu, Zhicheng Qiu, Xuanfu Li, Jian Yang, Lanjun Wang, Zili YiAbstract
Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video benchmarks. However, existing benchmarks rely predominantly on web-sourced videos that lack inter-clip spatiotemporal continuity, making it difficult to assess whether models can maintain consistent memory across days or weeks of real-world experience. We introduce EgoMonth, the first month-level egocentric video understanding benchmark. EgoMonth comprises over 300 hours of first-person daily-life recordings from 20 participants spanning 20 to 120 days, paired with 1,443 human-crafted multiple-choice question-answer pairs. We design a cognitively grounded 14-task evaluation framework organized into three hierarchical cognitive levels: Schema Consolidation, Episodic Indexing, and Cascading Reasoning. Evaluation of state-of-the-art open-source and closed-source MLLMs reveals that even the best-performing model, Gemini 2.5 Pro, achieves only 71.8% macro-average accuracy, remaining 22.4 percentage points below the corrected human baseline of 94.2%. Several models perform near or below the 25% chance level on tasks such as Route Reasoning, Cross-view Spatial Reasoning, and Direction Judgement, while even the strongest closed-source model remains substantially below human performance. These results indicate that current MLLMs function as lossy summarizers rather than faithful memorizers, highlighting the need for architectures with genuine long-term spatiotemporal memory.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13113
PDF
-
UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations
2026-08-13 10:00:27Peng Li, Qianqian Xu, Shilong Bao, Yangbangyan Jiang, Qingming HuangAbstract
Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents, violations, and interactions between vehicles and vulnerable road users. A useful system should explain how a traffic event develops, why it happens, and when the relevant interaction occurs, yet this remains difficult for multimodal large language models (MLLMs) because traffic videos contain sparse events and varied viewpoints. We introduce UniTraffic-Agent, the MR-CAS solution for Track~3 of the 10th AI City Challenge, which includes Traffic Anomaly Reasoning (TAR) and two out-of-domain evaluations: FETV for fisheye traffic events and PSI-VQA for pedestrian intention reasoning. UniTraffic-Agent follows an observe--reason--act--verify workflow that samples timestamped visual evidence, reasons over all questions from the same clip in one request, and converts responses through task-specific action adapters. On the official Public leaderboards, MR-CAS ranks 16th on TAR with a score of 0.5780, 2nd on FETV with 0.4884, and 4th on PSI-VQA with 64.4161. The code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13031
PDF
-
TennisVAR: A Stroke-Evidence-Grounded Multimodal Large Language Model for Tactical Reasoning in Tennis Videos
2026-08-13 08:01:22Yifan Mei, Qingling Shi, Changli Wu, Jiayuan Rao, Jiayi Ji, Liujuan CaoAbstract
Sports-video understanding is moving beyond event recognition toward explaining how actions collectively shape match progression, however, existing tennis-video methods either perceive individual strokes without modeling their tactical dependencies or generate high-level analyses without grounding them in the underlying events. To bridge this perception-to-understanding gap, we formulate stroke-evidence-grounded tactical reasoning, a new rally-level task that requires models to jointly predict an open-ended answer, a hierarchical tactic label, an ordered sequence of supporting strokes, and decisive key actions, with each evidence stroke anchored to its racket-ball contact frame. We further introduce TRACE (Tactical Reasoning with Action-Chain Evidence in Tennis), a large-scale expert-annotated benchmark containing 11,189 rally videos, 41,485 stroke events, 25,429 tactical units, and 11,189 question-answer pairs, which unifies fine-grained stroke attributes, cross-stroke tactical relations, hierarchical tactic annotations, and evidence-grounded questions across factual perception, tactical understanding, and decision reasoning. Building on TRACE, we propose TennisVAR (Tennis Video Action-chain Reasoner), an evidence-grounded multimodal large language model that follows an "event-relation-evidence-tactic" reasoning paradigm, where an Event Parsing Module converts continuous rallies into explicit stroke-event sequences while a Tactical Graph-Guided Temporal Reasoner jointly models rally progression and same-player decision dependencies to identify question-relevant evidence and decisive actions.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12920
PDF
