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

• URL: http://arxiv.org/abs/2404.16994v2
• Date: Mon, 29 Apr 2024 14:52:02 GMT
• Title: PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
• Authors: Lin Xu, Yilin Zhao, Daquan Zhou, Zhijie Lin, See Kiong Ng, Jiashi Feng,
• Abstract summary: Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources. This paper investigates a straight-forward, highly efficient, and resource-light approach to adapting an existing image-language pre-trained model for video understanding.
• Score: 78.23573511641548
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources, which hinders the progress of video-language models. This paper investigates a straight-forward, highly efficient, and resource-light approach to adapting an existing image-language pre-trained model for dense video understanding. Our preliminary experiments reveal that directly fine-tuning pre-trained image-language models with multiple frames as inputs on video datasets leads to performance saturation or even a drop. Our further investigation reveals that it is largely attributed to the bias of learned high-norm visual features. Motivated by this finding, we propose a simple but effective pooling strategy to smooth the feature distribution along the temporal dimension and thus reduce the dominant impacts from the extreme features. The new model is termed Pooling LLaVA, or PLLaVA in short. PLLaVA achieves new state-of-the-art performance on modern benchmark datasets for both video question-answer and captioning tasks. Notably, on the recent popular VideoChatGPT benchmark, PLLaVA achieves a score of 3.48 out of 5 on average of five evaluated dimensions, exceeding the previous SOTA results from GPT4V (IG-VLM) by 9%. On the latest multi-choice benchmark MVBench, PLLaVA achieves 58.1% accuracy on average across 20 sub-tasks, 14.5% higher than GPT4V (IG-VLM). Code is available at https://pllava.github.io/

Related papers

• An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models [65.37846460916042]
  We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs. We introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency.
  arXiv  Detail & Related papers  (2024-03-11T14:35:32Z)
• Video-LLaVA: Learning United Visual Representation by Alignment Before Projection [27.04277811443469]
  Video-LLaVA learns from a mixed dataset of images and videos, mutually enhancing each other. Video-LLaVA superior performances on a broad range of 9 image benchmarks across 5 image question-answering datasets and 4 image benchmark toolkits.
  arXiv  Detail & Related papers  (2023-11-16T10:59:44Z)
• VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending [78.1399386935455]
  Large-scale image-text contrastive pre-training models, such as CLIP, have been demonstrated to effectively learn high-quality multimodal representations. We propose a novel video-text pre-training method dubbed VLAB: Video Language pre-training by feature generativearity and Blending. VLAB transfers CLIP representations to video pre-training tasks and develops unified video multimodal models for a wide range of video-text tasks.
  arXiv  Detail & Related papers  (2023-05-22T15:54:22Z)
• VindLU: A Recipe for Effective Video-and-Language Pretraining [83.49216853881595]
  This paper conducts an empirical study demystifying the most important factors in the VidL model design. Using these empirical insights, we then develop a step-by-step recipe, dubbed VindLU, for effective VidL pretraining. Our model trained using our recipe achieves comparable or better than state-of-the-art results on several VidL tasks.
  arXiv  Detail & Related papers  (2022-12-09T18:54:05Z)
• LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling [48.283659682112926]
  We propose LiteVL, which adapts a pre-trained image-language model BLIP into a video-text model directly on downstream tasks. We also propose a non-parametric pooling mechanism to adaptively reweight the fine-grained video embedding conditioned on the text.
  arXiv  Detail & Related papers  (2022-10-21T13:03:49Z)
• Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation [79.72299298976525]
  We propose to augment a vision-language pre-training model with a textual pre-trained language model (PLM) via vision-language knowledge distillation (VLKD) Experiments show that the resulting model has strong zero-shot performance on multimodal generation tasks, such as open-ended visual question answering and image captioning. The original textual language understanding and generation ability of the PLM is maintained after VLKD, which makes our model versatile for both multimodal and unimodal tasks.
  arXiv  Detail & Related papers  (2022-03-12T09:33:37Z)
• Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions [31.4943447481144]
  We study joint and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream tasks. Our model achieves new state-of-the-art results in 10 understanding tasks and 2 more novel text-to-visual generation tasks.
  arXiv  Detail & Related papers  (2021-11-19T17:36:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.