UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark

• URL: http://arxiv.org/abs/2410.01180v1
• Date: Wed, 2 Oct 2024 02:33:09 GMT
• Title: UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark
• Authors: Hasnat Md Abdullah, Tian Liu, Kangda Wei, Shu Kong, Ruihong Huang,
• Abstract summary: Localizing unusual activities, such as human errors or surveillance incidents, in videos holds practical significance. To explore foundation models' capability in localizing unusual activity, we introduce UAL-Bench. UAL-Bench features three video datasets: UAG-OOPS, UAG- SSBD, UAG-FunQA, and an instruction-tune dataset: OOPS-UAG-Instruct. Our results show the VLM-LLM approach excels in localizing short-span unusual events and predicting their onset (start time) more accurately than Vid-LLMs.
• Score: 20.15425745473231
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Localizing unusual activities, such as human errors or surveillance incidents, in videos holds practical significance. However, current video understanding models struggle with localizing these unusual events likely because of their insufficient representation in models' pretraining datasets. To explore foundation models' capability in localizing unusual activity, we introduce UAL-Bench, a comprehensive benchmark for unusual activity localization, featuring three video datasets: UAG-OOPS, UAG-SSBD, UAG-FunQA, and an instruction-tune dataset: OOPS-UAG-Instruct, to improve model capabilities. UAL-Bench evaluates three approaches: Video-Language Models (Vid-LLMs), instruction-tuned Vid-LLMs, and a novel integration of Vision-Language Models and Large Language Models (VLM-LLM). Our results show the VLM-LLM approach excels in localizing short-span unusual events and predicting their onset (start time) more accurately than Vid-LLMs. We also propose a new metric, R@1, TD <= p, to address limitations in existing evaluation methods. Our findings highlight the challenges posed by long-duration videos, particularly in autism diagnosis scenarios, and the need for further advancements in localization techniques. Our work not only provides a benchmark for unusual activity localization but also outlines the key challenges for existing foundation models, suggesting future research directions on this important task.

Related papers

• Zero-shot Action Localization via the Confidence of Large Vision-Language Models [19.683461002518147]
  We introduce a true ZEro-shot Action localization method (ZEAL) Specifically, we leverage the built-in action knowledge of a large language model (LLM) to inflate actions into highly-detailed descriptions. We demonstrate remarkable results in zero-shot action localization on a challenging benchmark, without any training.
  arXiv  Detail & Related papers  (2024-10-18T09:51:14Z)
• Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization [44.00346424334902]
  We explore the scalability of self-training with unlabeled YouTube videos for temporal action localization (OV-TAL) Our approach consists of two stages: (1) a class-agnostic action localizer is trained on a human-labeled TAL dataset to generate pseudo-labels for unlabeled videos, and (2) the large-scale pseudo-labeled dataset is then used to train the localizer.
  arXiv  Detail & Related papers  (2024-07-09T16:44:04Z)
• VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs [64.60035916955837]
  VANE-Bench is a benchmark designed to assess the proficiency of Video-LMMs in detecting anomalies and inconsistencies in videos. Our dataset comprises an array of videos synthetically generated using existing state-of-the-art text-to-video generation models. We evaluate nine existing Video-LMMs, both open and closed sources, on this benchmarking task and find that most of the models encounter difficulties in effectively identifying the subtle anomalies.
  arXiv  Detail & Related papers  (2024-06-14T17:59:01Z)
• Open-Vocabulary Spatio-Temporal Action Detection [59.91046192096296]
  Open-vocabulary-temporal action detection (OV-STAD) is an important fine-grained video understanding task. OV-STAD requires training a model on a limited set of base classes with box and label supervision. To better adapt the holistic VLM for the fine-grained action detection task, we carefully fine-tune it on the localized video region-text pairs.
  arXiv  Detail & Related papers  (2024-05-17T14:52:47Z)
• Test-Time Zero-Shot Temporal Action Localization [58.84919541314969]
  ZS-TAL seeks to identify and locate actions in untrimmed videos unseen during training. Training-based ZS-TAL approaches assume the availability of labeled data for supervised learning. We introduce a novel method that performs Test-Time adaptation for Temporal Action localization (T3AL)
  arXiv  Detail & Related papers  (2024-04-08T11:54:49Z)
• Harnessing Large Language Models for Training-free Video Anomaly Detection [34.76811491190446]
  Video anomaly detection (VAD) aims to temporally locate abnormal events in a video. Training-based methods are prone to be domain-specific, thus being costly for practical deployment. We propose LAnguage-based VAD (LAVAD), a method tackling VAD in a novel, training-free paradigm.
  arXiv  Detail & Related papers  (2024-04-01T09:34:55Z)
• Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding [108.79026216923984]
  Video grounding aims to localize a-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary Spatio-Temporal Video Grounding task.
  arXiv  Detail & Related papers  (2023-12-31T13:53:37Z)
• Optimization Efficient Open-World Visual Region Recognition [55.76437190434433]
  RegionSpot integrates position-aware localization knowledge from a localization foundation model with semantic information from a ViL model. Experiments in open-world object recognition show that our RegionSpot achieves significant performance gain over prior alternatives.
  arXiv  Detail & Related papers  (2023-11-02T16:31:49Z)
• Dense Video Object Captioning from Disjoint Supervision [77.47084982558101]
  We propose a new task and model for dense video object captioning. This task unifies spatial and temporal localization in video. We show how our model improves upon a number of strong baselines for this new task.
  arXiv  Detail & Related papers  (2023-06-20T17:57:23Z)

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.