REVIEW 6 cited by
Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Recent advances in Large Language Models (LLMs) have enabled the development of Video-LLMs, advancing multimodal learning by bridging video data with language tasks. However, current video understanding models struggle with processing long video sequences, supporting multi-turn dialogues, and adapting to real-world dynamic scenarios. To address these issues, we propose StreamChat, a training-free framework for streaming video reasoning and conversational interaction. $\StreamChat$ leverages a novel hierarchical memory system to efficiently process and compress video features over extended sequences, enabling real-time, multi-turn dialogue. Our framework incorporates a parallel system scheduling strategy that enhances processing speed and reduces latency, ensuring robust performance in real-world applications. Furthermore, we introduce StreamBench, a versatile benchmark that evaluates streaming video understanding across diverse media types and interactive scenarios, including multi-turn interactions and complex reasoning tasks. Extensive evaluations on StreamBench and other public benchmarks demonstrate that StreamChat significantly outperforms existing state-of-the-art models in terms of accuracy and response times, confirming its effectiveness for streaming video understanding. Code is available at StreamChat: https://github.com/hmxiong/StreamChat.
Forward citations
Cited by 6 Pith papers
-
FOLIO: Focused Semantic Memory for Streaming Video Understanding
Entity-centered focus-guided streaming memory lifts Qwen3-VL-8B to 82.0/69.1 Perception/Backward on OVO-Bench and 74.5 on StreamingBench while cutting writer tokens by ~32%.
-
Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning
Question-guided dual geometric memories with relevance-novelty utility reportedly reach state-of-the-art video spatial reasoning on two in-domain and five out-of-distribution benchmarks.
-
Position: Modular Memory is the Key to Continual Learning Agents
A modular memory combining in-context learning and in-weight learning is proposed as the key to continual learning agents.
-
AdsQA: Towards Advertisement Video Understanding
AdsQA adds an ad-video question-answering benchmark and ReAd-R, a GRPO-trained model that beats 7B baselines but not larger closed models.
-
Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
A two-stage trained MLLM with a perception-to-cognition chain-of-thought and a self-verification RL reward outperforms prior models on video anomaly detection and reasoning.
-
Diffractive electroproduction of light vector particles: leading Fock-state contribution in the presence of significant higher Fock-state effects
The paper claims the leading quark-antiquark approximation in the color dipole model only matches HERA data for rho/gamma above Q^2 of 20 GeV^2 and for phi above Q^2 of 10 GeV^2, unlike J/psi.
Discussion (0). Continue with ORCID to comment.