Pith. sign in

REVIEW 6 cited by

Language Repository for Long Video Understanding

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2403.14622 v2 pith:MK3WJEVM submitted 2024-03-21 cs.CV

Kumara Kahatapitiya , Kanchana Ranasinghe , Jongwoo Park , Michael S. Ryoo This is my paper
classification cs.CV
keywords informationlanguagerepositoryvideointroducelangrepollmslong
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that focus on pruning redundancies in text, and extracting information at various temporal scales. The proposed framework is evaluated on zero-shot visual question-answering benchmarks including EgoSchema, NExT-QA, IntentQA and NExT-GQA, showing state-of-the-art performance at its scale. Our code is available at https://github.com/kkahatapitiya/LangRepo.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames

    cs.LG 2025-07 conditional novelty 6.0 of 10

    TCoT uses a single VLM to select question-relevant video frames from segments, then answers from that curated context, improving video QA accuracy across four benchmarks and three VLMs.

  2. Why Do Vision Language Models Struggle To Recognize Human Emotions?

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    VLMs fail at video emotion recognition because they collapse rare emotions into common ones and process frames as an unordered bag; summarizing skipped frames in text partially recovers temporal cues.

  3. Towards Sparse Video Understanding and Reasoning

    cs.CV 2026-02 conditional novelty 5.0 of 10

    A video-QA agent that carries only a structured text summary between rounds beats dense-frame baselines on accuracy while using a handful of frames per video.

  4. LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering

    cs.CV 2025-07 conditional novelty 5.0 of 10

    LeAdQA improves video question answering by using LLM-rewritten causal queries to drive temporal grounding that selects relevant video segments for the answering model.

  5. Empowering Multimodal LLMs with External Tools: A Comprehensive Survey

    cs.CV 2025-08 unverdicted novelty 2.0 of 10

    A survey paper maps how external tools are used to augment multimodal large language models across data, tasks, evaluation, and future directions.

  6. MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering

    cs.CV 2025-06

Pith tools