Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data

• URL: http://arxiv.org/abs/2407.13094v1
• Date: Thu, 18 Jul 2024 01:55:48 GMT
• Title: Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data
• Authors: Wufei Ma, Kai Li, Zhongshi Jiang, Moustafa Meshry, Qihao Liu, Huiyu Wang, Christian Häne, Alan Yuille,
• Abstract summary: We propose a novel evaluation task for video-text understanding, namely retrieval from counterfactually augmented data (RCAD) and a new Feint6K dataset. To succeed on our new evaluation task, models must derive a comprehensive understanding of the video from cross-frame reasoning. Our approach successfully learn more discriminative action embeddings and improves results on Feint6K when applied to multiple video-text models.
• Score: 19.210471935816273
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent video-text foundation models have demonstrated strong performance on a wide variety of downstream video understanding tasks. Can these video-text models genuinely understand the contents of natural videos? Standard video-text evaluations could be misleading as many questions can be inferred merely from the objects and contexts in a single frame or biases inherent in the datasets. In this paper, we aim to better assess the capabilities of current video-text models and understand their limitations. We propose a novel evaluation task for video-text understanding, namely retrieval from counterfactually augmented data (RCAD), and a new Feint6K dataset. To succeed on our new evaluation task, models must derive a comprehensive understanding of the video from cross-frame reasoning. Analyses show that previous video-text foundation models can be easily fooled by counterfactually augmented data and are far behind human-level performance. In order to narrow the gap between video-text models and human performance on RCAD, we identify a key limitation of current contrastive approaches on video-text data and introduce LLM-teacher, a more effective approach to learn action semantics by leveraging knowledge obtained from a pretrained large language model. Experiments and analyses show that our approach successfully learn more discriminative action embeddings and improves results on Feint6K when applied to multiple video-text models. Our Feint6K dataset and project page is available at https://feint6k.github.io.

Related papers

• Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs [20.168429351519055]
  Video understanding is a crucial next step for multimodal large language models (LMLMs) We propose VideoNIAH (Video Needle In A Haystack), a benchmark construction framework through synthetic video generation. We conduct a comprehensive evaluation of both proprietary and open-source models, uncovering significant differences in their video understanding capabilities.
  arXiv  Detail & Related papers  (2024-06-13T17:50:05Z)
• 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)
• InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation [90.71796406228265]
  InternVid is a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations. The InternVid dataset contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words.
  arXiv  Detail & Related papers  (2023-07-13T17:58:32Z)
• Learning a Grammar Inducer from Massive Uncurated Instructional Videos [118.7279072358029]
  Video-aided grammar induction aims to leverage video information for finding more accurate syntactic grammars for accompanying text. We build a new model that can better learn video-span correlation without manually designed features. Our model yields higher F1 scores than the previous state-of-the-art systems trained on in-domain data.
  arXiv  Detail & Related papers  (2022-10-22T00:22:55Z)
• Revealing Single Frame Bias for Video-and-Language Learning [115.01000652123882]
  We show that a single-frame trained model can achieve better performance than existing methods that use multiple frames for training. This result reveals the existence of a strong "static appearance bias" in popular video-and-language datasets. We propose two new retrieval tasks based on existing fine-grained action recognition datasets that encourage temporal modeling.
  arXiv  Detail & Related papers  (2022-06-07T16:28:30Z)
• Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval [70.30052749168013]
  Multi-channel video-language retrieval require models to understand information from different channels. contrastive multimodal models are shown to be highly effective at aligning entities in images/videos and text. There is not a clear way to quickly adapt these two lines to multi-channel video-language retrieval with limited data and resources.
  arXiv  Detail & Related papers  (2022-06-05T01:43:52Z)
• Video Summarization Based on Video-text Modelling [0.0]
  We propose a multimodal self-supervised learning framework to obtain semantic representations of videos. We also introduce a progressive video summarization method, where the important content in a video is pinpointed progressively to generate better summaries. An objective evaluation framework is proposed to measure the quality of video summaries based on video classification.
  arXiv  Detail & Related papers  (2022-01-07T15:21:46Z)
• VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation [124.02278735049235]
  VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task difficulty levels. We evaluate various baseline methods with and without large-scale VidL pre-training. The significant gap between our best model and human performance calls for future study for advanced VidL models.
  arXiv  Detail & Related papers  (2021-06-08T18:34:21Z)

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.