arXiv Computer Vision
Don't Pause! Every prediction matters in a streaming video
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 21
PACE: Plan, Attend, Check, and Emit for Training-Free Response Timing in Streaming Video Understanding
arXiv:2610.28323v1 Announce Type: new Abstract: Streaming video understanding requires a model to decide not only what to answer but also when to answer. Evidence arrives progressively, and recent be...
arXiv Computer Vision
Sep 30
APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants
arXiv:2609.37559v1 Announce Type: new Abstract: To serve as real-world personal assistants, streaming video models need persistent memory that retains past experiences for later use. Yet existing str...
arXiv Computation and Language
Oct 9
FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?
FastBench is a new benchmark that tests streaming Video‑Large‑Language Models (VLMs) on high‑dynamic real‑world video streams, where events occur rapidly and cannot be captured by sparse 1–2 FPS sampling. The benchmark uses a trajectory‑grounded pipeline that generates QA pairs from high‑FPS clips, filters questions answerable at 2 FPS, verifies answers with SAM3 and CoTracker3 trajectories, and incorporates three rounds of human inspection, yielding 306 QA pairs across eight domains and multiple temporal scopes. Experiments show that even the strongest model, Gemini‑3.5‑Flash, achieves only 50.7 % accuracy, and that denser sampling improves performance but saturates when history is compressed; a training‑free baseline, ProactiveFrame, outperforms uniform sampling but still falls short of oracle‑guided focusing.
arXiv Computation and Language
Sep 28
TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding
TRACE (Temporal Audit and Condition-aware Evaluation) is a new benchmark and evaluation framework for streaming video understanding that explicitly records when evidence becomes valid, how visual history is maintained, and how responses are triggered. It combines temporally audited visual tasks, evidence timing, instruction-dependent trigger annotations, a unified causal Core–Adapter protocol, and multidimensional reporting of answer quality, timeliness, response-selection behavior, workload, completion, and reliability. Using 1,240 records from 517 videos, TRACE evaluated eight publicly available models in eight configurations, revealing that similar QA accuracy can hide significant differences in completion, answer validity, generation workload, and proactive performance metrics such as response delay, false alarms, and missed target windows.
arXiv AI
Jun 8
Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding
arXiv:2606. 06991v1 Announce Type: cross Abstract: Online Video Large Language Models (Video-LLMs) have advanced toward seamless human-AI interaction through frame-by-frame processing and proactive responding.
arXiv AI
Jun 16
What Should a Streaming Video Model Remember?
arXiv:2606. 16353v1 Announce Type: cross Abstract: Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation budgets.