TVBench: Redesigning Video-Language Evaluation

• URL: http://arxiv.org/abs/2410.07752v2
• Date: Fri, 03 Jan 2025 11:21:25 GMT
• Title: TVBench: Redesigning Video-Language Evaluation
• Authors: Daniel Cores, Michael Dorkenwald, Manuel Mucientes, Cees G. M. Snoek, Yuki M. Asano,
• Abstract summary: We show that the currently most used video-language benchmarks can be solved without requiring much temporal reasoning. We propose TVBench, a novel open-source video multiple-choice question-answering benchmark.
• Score: 48.71203934876828
• License:
• Abstract: Large language models have demonstrated impressive performance when integrated with vision models even enabling video understanding. However, evaluating these video models presents its own unique challenges, for which several benchmarks have been proposed. In this paper, we show that the currently most used video-language benchmarks can be solved without requiring much temporal reasoning. We identified three main issues in existing datasets: (i) static information from single frames is often sufficient to solve the tasks (ii) the text of the questions and candidate answers is overly informative, allowing models to answer correctly without relying on any visual input (iii) world knowledge alone can answer many of the questions, making the benchmarks a test of knowledge replication rather than visual reasoning. In addition, we found that open-ended question-answering benchmarks for video understanding suffer from similar issues while the automatic evaluation process with LLMs is unreliable, making it an unsuitable alternative. As a solution, we propose TVBench, a novel open-source video multiple-choice question-answering benchmark, and demonstrate through extensive evaluations that it requires a high level of temporal understanding. Surprisingly, we find that most recent state-of-the-art video-language models perform similarly to random performance on TVBench, with only a few models such as Qwen2-VL, and Tarsier clearly surpassing this baseline.

Related papers

• CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding [43.858197893052115]
  CG-Bench is a novel benchmark for clue-grounded question answering in long videos. It features 1,219 manually curated videos categorized by a granular system with 14 primary categories, 171 secondary categories, and 638 tertiary categories. The benchmark includes 12,129 QA pairs in three major question types: perception, reasoning, and hallucination.
  arXiv  Detail & Related papers  (2024-12-16T18:46:45Z)
• Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering [13.294004180200496]
  We introduce Local-Global Question Aware Video Embedding (LGQAVE), which incorporates three major innovations to integrate multi-modal knowledge better. LGQAVE moves beyond traditional ad-hoc frame sampling by utilizing a cross-attention mechanism that precisely identifies the most relevant frames concerning the questions. An additional cross-attention module integrates these local and global embeddings to generate the final video embeddings, which a language model uses to generate answers.
  arXiv  Detail & Related papers  (2024-12-12T12:39:07Z)
• TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models [75.42002690128486]
  TemporalBench is a new benchmark dedicated to evaluating fine-grained temporal understanding in videos. It consists of 10K video question-answer pairs, derived from 2K high-quality human annotations detailing the temporal dynamics in video clips. Results show that state-of-the-art models like GPT-4o achieve only 38.5% question answering accuracy on TemporalBench.
  arXiv  Detail & Related papers  (2024-10-14T17:59:58Z)
• 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)
• Grounded Question-Answering in Long Egocentric Videos [39.281013854331285]
  open-ended question-answering (QA) in long, egocentric videos allows individuals or robots to inquire about their own past visual experiences. This task presents unique challenges, including the complexity of temporally grounding queries within extensive video content. Our proposed approach tackles these challenges by (i) integrating query grounding and answering within a unified model to reduce error propagation.
  arXiv  Detail & Related papers  (2023-12-11T16:31:55Z)
• MVBench: A Comprehensive Multi-modal Video Understanding Benchmark [63.14000659130736]
  We introduce a comprehensive Multi-modal Video understanding Benchmark, namely MVBench. We first introduce a novel static-to-dynamic method to define these temporal-related tasks. Then, guided by the task definition, we automatically convert public video annotations into multiple-choice QA to evaluate each task.
  arXiv  Detail & Related papers  (2023-11-28T17:59:04Z)
• Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models [81.84810348214113]
  Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. To guide the development of such a model, the establishment of a robust and comprehensive evaluation system becomes crucial. This paper proposes textitVideo-Bench, a new comprehensive benchmark along with a toolkit specifically designed for evaluating Video-LLMs.
  arXiv  Detail & Related papers  (2023-11-27T18:59:58Z)
• Video Question Answering with Iterative Video-Text Co-Tokenization [77.66445727743508]
  We propose a novel multi-stream video encoder for video question answering. We experimentally evaluate the model on several datasets, such as MSRVTT-QA, MSVD-QA, IVQA. Our model reduces the required GFLOPs from 150-360 to only 67, producing a highly efficient video question answering model.
  arXiv  Detail & Related papers  (2022-08-01T15:35:38Z)
• Fill-in-the-blank as a Challenging Video Understanding Evaluation Framework [19.031957183047048]
  We introduce a novel dataset consisting of 28,000 videos and fill-in-the-blank tests. We show that both a multimodal model and a strong language model have a large gap with human performance.
  arXiv  Detail & Related papers  (2021-04-09T04:00:10Z)
• Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [96.10612095576333]
  We propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. Our model is also comprised of dual-level attention (word/object and frame level), multi-head self-cross-integration for different sources (video and dense captions), and which pass more relevant information to gates. We evaluate our model on the challenging TVQA dataset, where each of our model components provides significant gains, and our overall model outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2020-05-13T16:35:27Z)

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.