FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks

• URL: http://arxiv.org/abs/2203.13371v1
• Date: Thu, 24 Mar 2022 22:35:00 GMT
• Title: FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks
• Authors: Santiago Castro and Fabian Caba Heilbron
• Abstract summary: Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks. We present a fine-tuning strategy to refine these models for zero-shot video understanding tasks.
• Score: 3.832696393393788
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval. However, these models haven't been adapted to video, mainly because they don't account for the time dimension but also because video frames are different from the typical images (e.g., containing motion blur, less sharpness). In this paper, we present a fine-tuning strategy to refine these large-scale pretrained image-text models for zero-shot video understanding tasks. We show that by carefully adapting these models we obtain considerable improvements on two zero-shot Action Recognition tasks and three zero-shot Text-to-video Retrieval tasks. The code is available at https://github.com/bryant1410/fitclip

Related papers

• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• Harvest Video Foundation Models via Efficient Post-Pretraining [67.30842563833185]
  We propose an efficient framework to harvest video foundation models from image ones. Our method is intuitively simple by randomly dropping input video patches and masking out input text during the post-pretraining procedure. Our method achieves state-of-the-art performances, which are comparable to some heavily pretrained video foundation models.
  arXiv  Detail & Related papers  (2023-10-30T14:06:16Z)
• Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks [6.925770576386087]
  We propose a detailed study on the generalization abilities of image-text models when evaluated on video understanding tasks in a zero-shot setting. Our experiments show that image-text models exhibit impressive performance on video AR, video RT and video MC. These findings shed a light on the benefits of adapting foundational image-text models to an array of video tasks while avoiding the costly pretraining step.
  arXiv  Detail & Related papers  (2023-10-07T20:57:54Z)
• TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale [59.01246141215051]
  We analyze the factor that leads to degradation from the perspective of language supervision. We propose a tunable-free pre-training strategy to retain the generalization ability of the text encoder. We produce a series of models, dubbed TVTSv2, with up to one billion parameters.
  arXiv  Detail & Related papers  (2023-05-23T15:44:56Z)
• Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models [68.31777975873742]
  Recent attempts at video editing require significant text-to-video data and computation resources for training. We propose vid2vid-zero, a simple yet effective method for zero-shot video editing. Experiments and analyses show promising results in editing attributes, subjects, places, etc., in real-world videos.
  arXiv  Detail & Related papers  (2023-03-30T17:59:25Z)
• MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge [35.45809761628721]
  Large scale Vision-Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. We propose an unsupervised approach to tuning video data for best zero-shot action recognition performance. Our resulting models demonstrate high transferability to numerous unseen zero-shot downstream tasks.
  arXiv  Detail & Related papers  (2023-03-15T20:17:41Z)
• Frozen CLIP Models are Efficient Video Learners [86.73871814176795]
  Video recognition has been dominated by the end-to-end learning paradigm. Recent advances in Contrastive Vision-Language Pre-training pave the way for a new route for visual recognition tasks. We present Efficient Video Learning -- an efficient framework for directly training high-quality video recognition models.
  arXiv  Detail & Related papers  (2022-08-06T17:38:25Z)
• Expanding Language-Image Pretrained Models for General Video Recognition [136.0948049010682]
  Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data. We present a simple yet effective approach that adapts the pretrained language-image models to video recognition directly. Our approach surpasses the current state-of-the-art methods by +7.6% and +14.9% in terms of top-1 accuracy under two popular protocols.
  arXiv  Detail & Related papers  (2022-08-04T17:59:54Z)
• TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification [26.12591949900602]
  We formulate a text-based task conditioner to adapt video features to the few-shot learning task. Our model obtains state-of-the-art performance on four challenging benchmarks in few-shot video action classification.
  arXiv  Detail & Related papers  (2021-06-21T15:08:08Z)

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.