SPOT! Revisiting Video-Language Models for Event Understanding

• URL: http://arxiv.org/abs/2311.12919v2
• Date: Fri, 1 Dec 2023 17:33:55 GMT
• Title: SPOT! Revisiting Video-Language Models for Event Understanding
• Authors: Gengyuan Zhang, Jinhe Bi, Jindong Gu, Yanyu Chen, Volker Tresp
• Abstract summary: We introduce SPOT Prober, to benchmark existing video-language models's capacities of distinguishing event-level discrepancies. We evaluate the existing video-language models with these positive and negative captions and find they fail to distinguish most of the manipulated events. Based on our findings, we propose to plug in these manipulated event captions as hard negative samples and find them effective in enhancing models for event understanding.
• Score: 31.49859545456809
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding videos is an important research topic for multimodal learning. Leveraging large-scale datasets of web-crawled video-text pairs as weak supervision has become a pre-training paradigm for learning joint representations and showcased remarkable potential in video understanding tasks. However, videos can be multi-event and multi-grained, while these video-text pairs usually contain only broad-level video captions. This raises a question: with such weak supervision, can video representation in video-language models gain the ability to distinguish even factual discrepancies in textual description and understand fine-grained events? To address this, we introduce SPOT Prober, to benchmark existing video-language models's capacities of distinguishing event-level discrepancies as an indicator of models' event understanding ability. Our approach involves extracting events as tuples (<Subject, Predicate, Object, Attribute, Timestamps>) from videos and generating false event tuples by manipulating tuple components systematically. We reevaluate the existing video-language models with these positive and negative captions and find they fail to distinguish most of the manipulated events. Based on our findings, we propose to plug in these manipulated event captions as hard negative samples and find them effective in enhancing models for event understanding.

Related papers

• ViLLa: Video Reasoning Segmentation with Large Language Model [48.75470418596875]
  We propose a new video segmentation task - video reasoning segmentation. The task is designed to output tracklets of segmentation masks given a complex input text query. We present ViLLa: Video reasoning segmentation with a Large Language Model.
  arXiv  Detail & Related papers  (2024-07-18T17:59:17Z)
• VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools [44.78291853329394]
  textbfVidCoM is a fast adaptive framework that leverages Large Language Models (LLMs) to reason about videos using lightweight visual tools. An InsOVER algorithm locates the corresponding video events based on an efficient Hungarian matching between decompositions of linguistic instructions and video events.
  arXiv  Detail & Related papers  (2023-10-16T17:05:56Z)
• 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)
• Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners [167.0346394848718]
  We propose VidIL, a few-shot Video-language Learner via Image and Language models. We use the image-language models to translate the video content into frame captions, object, attribute, and event phrases. We then instruct a language model, with a prompt containing a few in-context examples, to generate a target output from the composed content.
  arXiv  Detail & Related papers  (2022-05-22T05:18:27Z)
• Towards Diverse Paragraph Captioning for Untrimmed Videos [40.205433926432434]
  Existing approaches mainly solve the problem in two steps: event detection and then event captioning. We propose a paragraph captioning model which eschews the problematic event detection stage and directly generates paragraphs for untrimmed videos.
  arXiv  Detail & Related papers  (2021-05-30T09:28:43Z)
• Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions [75.77044856100349]
  We present the Spoken Moments dataset of 500k spoken captions each attributed to a unique short video depicting a broad range of different events. We show that our AMM approach consistently improves our results and that models trained on our Spoken Moments dataset generalize better than those trained on other video-caption datasets.
  arXiv  Detail & Related papers  (2021-05-10T16:30:46Z)
• Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language [148.0843278195794]
  We propose a new model architecture for learning multi-modal neuro-symbolic representations for video captioning. Our approach uses a dictionary learning-based method of learning relations between videos and their paired text descriptions.
  arXiv  Detail & Related papers  (2020-11-18T20:21:19Z)
• VIOLIN: A Large-Scale Dataset for Video-and-Language Inference [103.7457132841367]
  We introduce a new task, Video-and-Language Inference, for joint multimodal understanding of video and text. Given a video clip with subtitles aligned as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip. A new large-scale dataset, named Violin (VIdeO-and-Language INference), is introduced for this task, which consists of 95,322 video-hypothesis pairs from 15,887 video clips.
  arXiv  Detail & Related papers  (2020-03-25T20:39:05Z)

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.