REVIEW 6 cited by
ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding
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
Video Large Language Models (VideoLLMs) have made significant strides in video understanding but struggle with long videos due to the limitations of their backbone LLMs. Existing solutions rely on length extrapolation, which is memory-constrained, or visual token compression, which primarily leverages low-level temporal redundancy while overlooking the more effective high-level knowledge redundancy. To address this, we propose $\textbf{ReTaKe}$, a training-free method with two novel modules DPSelect and PivotKV, to jointly reduce both temporal visual redundancy and knowledge redundancy for video compression. To align with the way of human temporal perception, DPSelect identifies keyframes based on inter-frame distance peaks. To leverage LLMs' learned prior knowledge, PivotKV marks the keyframes as pivots and compress non-pivot frames by pruning low-attention tokens in their KV cache. ReTaKe enables VideoLLMs to process 8 times longer frames (up to 2048), outperforming similar-sized models by 3-5% and even rivaling much larger ones on VideoMME, MLVU, LongVideoBench, and LVBench. Moreover, by overlapping compression operations with prefilling, ReTaKe introduces only ~10% prefilling latency overhead while reducing decoding latency by ~20%. Our code is available at https://github.com/SCZwangxiao/video-ReTaKe.
Forward citations
Cited by 6 Pith papers
-
LongAnimation: Long Animation Generation with Dynamic Global-Local Memory
LongAnimation uses a dynamic global-local memory, built from a long-video-understanding model's KV cache, to colorize animation sequences of about 500 frames with stable color consistency.
-
Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
Flash-VStream uses a two-memory design (clustered low-res summaries plus high-res key-frame details) to answer questions about long videos with state-of-the-art benchmark scores and sub-second latency.
-
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
Nar-KFC improves long-video question answering by interleaving query-relevant diverse keyframes with captions of non-keyframes, raising accuracy on Video-MME, LongVideoBench, and MLVU across 7B MLLMs.
-
Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification
Video-XL-2 cuts long-video inference cost with chunked pre-filling and query-gated dense-or-sparse KV reloading, reporting half the FLOPs and a third less decoding memory at roughly equal benchmark scores.
-
A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
The paper claims 92.6% dynamic visual-token pruning with retained (or 110% of) baseline VQA performance, but the full text supplied is a different paper, so the claim is unverifiable here.
-
A Survey on Video Temporal Grounding with Multimodal Large Language Model
A taxonomized review of video temporal grounding with multimodal large language models, covering model roles, training paradigms, feature processing, benchmarks, and open problems.
Discussion (0). Sign in to comment.