arXiv Computer Vision
TraCE: Trajectory-Aware Concepts for Explainable Video Understanding
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 21
AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents
AgentVidBench is a new multi‑hop video question‑answering benchmark designed to evaluate spatial, temporal, and causal reasoning in multimodal large language models (MLLMs). Unlike existing tests that focus on simple scene queries or global summaries, AgentVidBench includes step‑by‑step solution traces to assess whether agents gather the necessary evidence to justify their answers. Experiments with 12 MLLMs show limited single‑turn performance, but integrating these models into agentic workflows improves both accuracy and trajectory scores, establishing AgentVidBench as a comprehensive testbed for future research on agentic video understanding.
arXiv Computer Vision
Sep 30
A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding
arXiv:2603.14733v2 Announce Type: replace Abstract: Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos...
arXiv AI
Jun 8
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
arXiv:2606. 07433v1 Announce Type: cross Abstract: Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video scenarios.
arXiv Computation and Language
Sep 25
STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models
STRAND is a new benchmark that tests multimodal large language models’ ability to track objects, their states, and relationships over time in videos. It evaluates intermediate reasoning by breaking queries into sub‑questions and uses Faithful Accuracy to ensure all parts of an answer are correct. The authors also propose an object‑centric framework that builds structured trajectories and shows reduced hallucinations and better temporal consistency compared to existing models.
arXiv AI
Sep 10
TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs
TimeBlind is a diagnostic benchmark designed to evaluate fine‑grained spatio‑temporal compositionality in video large language models (LLMs). It categorizes temporal understanding into three levels—atomic event recognition, event property characterization, and reasoning about event interdependencies—and uses a minimal‑pairs paradigm where video pairs share identical static content but differ only in temporal structure. Across 20 state‑of‑the‑art MLLMs tested on 600 curated instances, the best model achieved only 48.2% instance accuracy, far below human performance of 98.2%, highlighting a reliance on static visual shortcuts rather than true temporal reasoning.
arXiv Computer Vision
Aug 27
Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding
The paper introduces Clue-OPSD, a clue‑privileged on‑policy self‑distillation framework that improves long‑video understanding by focusing on short, question‑relevant clue intervals rather than the entire video. Experiments on multiple benchmarks and Qwen3.5 model scales show that this approach consistently outperforms standard backbone models and competes strongly with supervised post‑training baselines, all while requiring fewer input frames and no additional inference modules.