Pith. sign in

REVIEW 19 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

arxiv 2501.13468 v1 pith:AP6LRYXT submitted 2025-01-23 cs.CV cs.AI

Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

classification cs.CV cs.AI
keywords videostreamchatstreamingunderstandingmodelsmulti-turnframeworkinteraction
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks

    cs.CV 2026-06 unverdicted novelty 7.0

    M³Eval is a new cognitively-grounded benchmark that evaluates memory dimensions in multi-modal video models and reports consistent model weaknesses in disentanglement, interference, spatial-temporal grounding, and sym...

  2. EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision

    cs.CV 2026-05 unverdicted novelty 7.0

    Egostream introduces a diagnostic benchmark that expands 2,250 questions into 8,528 recall-conditioned evaluations to measure streaming episodic memory performance across detail, spatial, temporal, event, social, caus...

  3. Don't Pause! Every prediction matters in a streaming video

    cs.CV 2026-04 unverdicted novelty 7.0

    SPOT-Bench tests real-time streaming video perception with timeliness metrics, exposing limitations in current models and introducing AsynKV as an improved baseline.

  4. OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning

    cs.CV 2026-04 unverdicted novelty 7.0

    OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.

  5. Online Reasoning Video Object Segmentation

    cs.CV 2026-04 unverdicted novelty 7.0

    The work introduces the ORVOS task, the ORVOSB benchmark with causal annotations across 210 videos, and a baseline using updated prompts plus a temporal token reservoir.

  6. StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos

    cs.CV 2025-12 unverdicted novelty 7.0

    StreamGaze is a new benchmark and QA generation pipeline that measures how well MLLMs leverage gaze trajectories for temporal reasoning and proactive intention prediction in streaming egocentric videos.

  7. Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding

    cs.CV 2026-06 unverdicted novelty 6.0

    LyraV uses FDTC and SToP for per-frame incremental decoding to reach 98.29% video synchrony at 3.89 FPS while preserving general understanding.

  8. Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning

    cs.CV 2026-05 unverdicted novelty 6.0

    Q-GeoMem uses question-guided scoring to maintain a Fine-Grained Context Bank and Semantic-Geometric Evidence Bank, achieving SOTA on VSI-Bench and VSTI-Bench.

  9. IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams

    cs.CV 2026-05 unverdicted novelty 6.0

    IPIBench evaluates MLLMs on interactive proactive intelligence in streaming videos, identifies unstable triggering and poor coordination, and proposes the training-free IPI-Agent framework to improve performance acros...

  10. StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering

    cs.CV 2026-05 unverdicted novelty 6.0

    StreamOV proposes evidence-guided long-short term memory and a hidden-state-driven trigger for efficient online audio-visual reasoning in streaming videos, along with the SOVBench benchmark for multi-turn evaluation.

  11. Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

    cs.CV 2026-05 unverdicted novelty 6.0

    Response-G1 uses query-guided scene graphs, memory retrieval, and augmented prompting to improve when Video-LLMs decide to respond during streaming videos.

  12. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

    cs.CV 2026-01 unverdicted novelty 6.0

    HERMES organizes the KV cache into a hierarchical memory to enable real-time streaming video understanding in MLLMs, achieving 10x faster TTFT and up to 11.4% accuracy gains on streaming benchmarks with 68% fewer tokens.

  13. Streaming Video Instruction Tuning

    cs.CV 2025-12 unverdicted novelty 6.0

    Streamo is a streaming video LLM trained end-to-end on the new Streamo-Instruct-465K dataset that unifies multiple real-time video tasks with claimed strong temporal reasoning and generalization.

  14. ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference

    cs.CV 2026-06 unverdicted novelty 5.0

    ViCoStream is a new coordinated pipeline framework for streaming VideoLLMs that achieves 134 FPS video throughput and less than 50 ms TTFT on A100 while keeping accuracy near full-history baselines.

  15. LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams

    cs.CV 2026-06 unverdicted novelty 5.0

    LiveStarPro uses SVeD for response timing via perplexity, SCAM for incremental alignment, and TSHM for event-chain memory to achieve 28.9% better semantic correctness and 1.58x speedup on long video streams.

  16. Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning

    cs.CV 2026-05 unverdicted novelty 5.0

    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.

  17. Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

    cs.CV 2026-05 unverdicted novelty 5.0

    Response-G1 uses query-guided scene graph generation, memory retrieval, and retrieval-augmented prompting to improve proactive response timing in streaming video understanding.

  18. StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding

    cs.CV 2026-04 unverdicted novelty 5.0

    StreamMeCo compresses agent memory by 70% in streaming video understanding, yielding 1.87x faster retrieval and 1% higher average accuracy on benchmarks.

  19. Seed1.5-VL Technical Report

    cs.CV 2025-05 unverdicted novelty 4.0

    Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.