Pith. sign in

REVIEW 4 cited by

VTimeLLM: Empower LLM to Grasp Video Moments

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 2311.18445 v1 pith:SG7DYQLF submitted 2023-11-30 cs.CV

classification cs.CV
keywords videollmsunderstandingvtimellmexistingfine-grainedtemporalvideos
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have shown remarkable text understanding capabilities, which have been extended as Video LLMs to handle video data for comprehending visual details. However, existing Video LLMs can only provide a coarse description of the entire video, failing to capture the precise start and end time boundary of specific events. In this paper, we solve this issue via proposing VTimeLLM, a novel Video LLM designed for fine-grained video moment understanding and reasoning with respect to time boundary. Specifically, our VTimeLLM adopts a boundary-aware three-stage training strategy, which respectively utilizes image-text pairs for feature alignment, multiple-event videos to increase temporal-boundary awareness, and high-quality video-instruction tuning to further improve temporal understanding ability as well as align with human intents. Extensive experiments demonstrate that in fine-grained time-related comprehension tasks for videos such as Temporal Video Grounding and Dense Video Captioning, VTimeLLM significantly outperforms existing Video LLMs. Besides, benefits from the fine-grained temporal understanding of the videos further enable VTimeLLM to beat existing Video LLMs in video dialogue benchmark, showing its superior cross-modal understanding and reasoning abilities.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. TimePLE: Rethinking Temporal Representation for Video Temporal Grounding

    cs.CV 2026-07 conditional novelty 6.0 of 10

    TimePLE predicts a whole video interval as a joint distribution over a position-duration square, rather than predicting start and end separately, and reports higher mIoU across four VTG benchmarks.

  2. VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

    cs.CV 2026-07 conditional novelty 6.0 of 10

    An open 4B video MLLM with inflated-3D ViT tokenization and adaptive streaming perception outperforms comparable open models on general, long-video, and streaming benchmarks while using fewer visual tokens.

  3. PDB-Eval: An Evaluation of Large Multimodal Models for Description and Explanation of Personalized Driving Behavior

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Introduces PDB-Eval, a dual-view benchmark for fine-grained driver behavior description and explanation, and shows fine-tuning on it boosts performance on driving QA and downstream intention and recognition tasks.

  4. VideoRoPE: What Makes for Good Video Rotary Position Embedding?

    cs.CV 2025-02 conditional novelty 6.0 of 10

    VideoRoPE improves video rotary position embedding by allocating low-frequency channels to time, interleaving spatial channels, and adding tunable temporal spacing, beating prior RoPE variants on long-video benchmarks.

Pith tools