pith. sign in
Pith Number

pith:BUZ7W4MF

pith:2024:BUZ7W4MF2MBT2C65V4HB3BKU6K
not attested not anchored not stored refs resolved

PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning

Daquan Zhou, Jiashi Feng, Lin Xu, See Kiong Ng, Yilin Zhao, Zhijie Lin

A parameter-free temporal pooling strategy lets image-language models extend directly to video dense captioning and question answering without added parameters or heavy retraining.

arxiv:2404.16994 v2 · 2024-04-25 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{BUZ7W4MF2MBT2C65V4HB3BKU6K}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

PLLaVA achieves 3.48/5 on VideoChatGPT (9% above GPT-4V IG-VLM) and 58.1% on MVBench (14.5% above GPT-4V IG-VLM) by applying a parameter-free temporal pooling strategy that mitigates high-norm feature bias.

C2weakest assumption

That the performance drop when feeding multiple frames directly is caused primarily by high-norm visual feature bias rather than by other factors such as temporal modeling capacity or training data mismatch.

C3one line summary

A temporal pooling layer added to LLaVA smooths video feature distributions and lifts performance on dense video captioning and QA to new SOTA levels without extra parameters.

References

53 extracted · 53 resolved · 9 Pith anchors

[1] GPT-4 Technical Report 2023 · arXiv:2303.08774
[2] Frozen in time: A joint video and image encoder for end-to-end retrieval 2021
[3] Videollm: Modeling video sequence with large language models 2023
[4] Evaluating Large Language Models Trained on Code 2021 · arXiv:2107.03374
[5] Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality 2023

Formal links

1 machine-checked theorem link

Cited by

32 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:50.286434Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

0d33fb7185d3033d0bddaf0e1d8554f28a4ebede14e0f23f82c674abe7cb32e0

Aliases

arxiv: 2404.16994 · arxiv_version: 2404.16994v2 · doi: 10.48550/arxiv.2404.16994 · pith_short_12: BUZ7W4MF2MBT · pith_short_16: BUZ7W4MF2MBT2C65 · pith_short_8: BUZ7W4MF
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/BUZ7W4MF2MBT2C65V4HB3BKU6K \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 0d33fb7185d3033d0bddaf0e1d8554f28a4ebede14e0f23f82c674abe7cb32e0
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "00e0c64dde30021d2f834453a2d09e667f67fe7f2f1ae48439d07281cc292fe5",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-04-25T19:29:55Z",
    "title_canon_sha256": "f6dc7cafb3ca23a25cca7272ff45a3eee92caa94cdd7e103c0d0d8552bddf719"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2404.16994",
    "kind": "arxiv",
    "version": 2
  }
}