Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events

• URL: http://arxiv.org/abs/2408.04873v2
• Date: Sun, 08 Jun 2025 23:08:54 GMT
• Title: Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events
• Abstract summary: State-of-the-art automatic event detection struggles with interpretability and adaptability to evolving key events.<n>This paper introduces a novel task, episode detection, which identifies episodes within a news corpus of key event articles.<n>We introduce EpiMine, an unsupervised framework that identifies a key event's candidate episodes by leveraging natural episodic partitions in articles.
• Score: 32.6146580586496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art automatic event detection struggles with interpretability and adaptability to evolving large-scale key events -- unlike episodic structures, which excel in these areas. Often overlooked, episodes represent cohesive clusters of core entities performing actions at a specific time and location; a partially ordered sequence of episodes can represent a key event. This paper introduces a novel task, episode detection, which identifies episodes within a news corpus of key event articles. Detecting episodes poses unique challenges, as they lack explicit temporal or locational markers and cannot be merged using semantic similarity alone. While large language models (LLMs) can aid with these reasoning difficulties, they suffer with long contexts typical of news corpora. To address these challenges, we introduce EpiMine, an unsupervised framework that identifies a key event's candidate episodes by leveraging natural episodic partitions in articles, estimated through shifts in discriminative term combinations. These candidate episodes are more cohesive and representative of true episodes, synergizing with LLMs to better interpret and refine them into final episodes. We apply EpiMine to our three diverse, real-world event datasets annotated at the episode level, where it achieves a 59.2% average gain across all metrics compared to baselines.

Related papers

• Unified Video Dense Prediction from Disjoint Data [71.9957801898161]
  We introduce UniD, a unified video model that jointly predicts eight dense scene properties-depth, surface normals, semantic segmentation, boundaries, human parts, albedo, shading, and materials.<n>We propose a simple yet effective distillation step in which per-task experts supervise a unified backbone through lightweight task projectors.<n>UniD achieves competitive performance against per-task specialists and multi-task baselines.
  arXiv  Detail & Related papers  (2026-07-23T17:59:50Z)
• EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling [27.99622587517494]
  We introduce EpiPersona, a framework for explicit persona-episode coupling.<n>EpiPersona first projects noisy preference feedback into a low-dimensional persona space.<n>The inferred persona representation is then coupled with the current episode, enabling episode-aware preference prediction.
  arXiv  Detail & Related papers  (2026-03-30T09:04:24Z)
• E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching [87.38371267983263]
  Temporal Video Grounding aims to precisely localize time segments corresponding to query events.<n>E.M.Ground is a novel Vid-LLM for TVG that focuses on holistic and coherent event perception.<n>E.M.Ground consistently outperforms state-of-the-art Vid-LLMs by significant margins.
  arXiv  Detail & Related papers  (2026-02-05T02:16:00Z)
• VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models [8.155587933125673]
  Existing research has primarily focused on hallucinations involving the presence of events, objects, and scenes in videos.<n>We introduce a novel benchmark for evaluating the Video Event Relation Hallucination, named VERHallu.
  arXiv  Detail & Related papers  (2026-01-15T02:40:41Z)
• Grounding Partially-Defined Events in Multimodal Data [61.0063273919745]
  We introduce a multimodal formulation for partially-defined events and cast the extraction of these events as a three-stage span retrieval task. We propose a benchmark for this task, MultiVENT-G, that consists of 14.5 hours of densely annotated current event videos and 1,168 text documents, containing 22.8K labeled event-centric entities. Results illustrate the challenges that abstract event understanding poses and demonstrates promise in event-centric video-language systems.
  arXiv  Detail & Related papers  (2024-10-07T17:59:48Z)
• Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM [47.786978666537436]
  We propose a Two-Stage Prefix-Enhanced MLLM (TSPE) approach for event attribution in movie videos. In the local stage, we introduce an interaction-aware prefix that guides the model to focus on the relevant multimodal information within a single clip. In the global stage, we strengthen the connections between associated events using an inferential knowledge graph.
  arXiv  Detail & Related papers  (2024-09-14T08:30:59Z)
• "Previously on ..." From Recaps to Story Summarization [13.311411816150551]
  We introduce multimodal story summarization by leveraging TV episode recaps. Story summarization labels are unlocked by matching recap shots to corresponding sub-stories in the episode. We present a thorough evaluation on story summarization, including promising cross-series generalization.
  arXiv  Detail & Related papers  (2024-05-19T09:09:54Z)
• Glance and Focus: Memory Prompting for Multi-Event Video Question Answering [36.00733800536469]
  VideoQA has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Humans can easily tackle it by using a series of episode memories as anchors to quickly locate question-related key moments for reasoning. We propose the Glance-Focus model to mimic this effective reasoning strategy.
  arXiv  Detail & Related papers  (2024-01-03T03:51:16Z)
• SPOT! Revisiting Video-Language Models for Event Understanding [31.49859545456809]
  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.
  arXiv  Detail & Related papers  (2023-11-21T18:43:07Z)
• Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model [70.97446870672069]
  Video anomaly detection (VAD) has been paid increasing attention due to its potential applications. Video Anomaly Retrieval ( VAR) aims to pragmatically retrieve relevant anomalous videos by cross-modalities. We present two benchmarks, UCFCrime-AR and XD-Violence, constructed on top of prevalent anomaly datasets.
  arXiv  Detail & Related papers  (2023-07-24T06:22:37Z)
• Abnormal Event Detection via Hypergraph Contrastive Learning [54.80429341415227]
  Abnormal event detection plays an important role in many real applications. In this paper, we study the unsupervised abnormal event detection problem in Attributed Heterogeneous Information Network. A novel hypergraph contrastive learning method, named AEHCL, is proposed to fully capture abnormal event patterns.
  arXiv  Detail & Related papers  (2023-04-02T08:23:20Z)
• Unifying Event Detection and Captioning as Sequence Generation via Pre-Training [53.613265415703815]
  We propose a unified pre-training and fine-tuning framework to enhance the inter-task association between event detection and captioning. Our model outperforms the state-of-the-art methods, and can be further boosted when pre-trained on extra large-scale video-text data.
  arXiv  Detail & Related papers  (2022-07-18T14:18:13Z)
• Unsupervised Key Event Detection from Massive Text Corpora [42.31889135421941]
  We propose a new task, key event detection at the intermediate level, aiming to detect from a news corpus key events. This task can bridge event understanding and structuring and is inherently challenging because of the thematic and temporal closeness of key events. We develop an unsupervised key event detection framework, EvMine, that extracts temporally frequent peak phrases using a novel ttf-itf score.
  arXiv  Detail & Related papers  (2022-06-08T20:31:02Z)
• Learning Temporal Rules from Noisy Timeseries Data [72.93572292157593]
  We focus on uncovering the underlying atomic events and their relations that lead to the composite events within a noisy temporal data setting. We propose a Neural Temporal Logic Programming (Neural TLP) which first learns implicit temporal relations between atomic events and then lifts logic rules for supervision.
  arXiv  Detail & Related papers  (2022-02-11T01:29:02Z)
• On Hard Episodes in Meta-Learning [35.46163595112011]
  Existing meta-learners primarily focus on improving the average task accuracy across multiple episodes. Different episodes, however, may vary in hardness and quality leading to a wide gap in the meta-learner's performance across episodes.
  arXiv  Detail & Related papers  (2021-10-21T14:58:58Z)
• Learning Constraints and Descriptive Segmentation for Subevent Detection [74.48201657623218]
  We propose an approach to learning and enforcing constraints that capture dependencies between subevent detection and EventSeg prediction. We adopt Rectifier Networks for constraint learning and then convert the learned constraints to a regularization term in the loss function of the neural model.
  arXiv  Detail & Related papers  (2021-09-13T20:50:37Z)
• A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games [3.7111751305143654]
  We present a universal taxonomy that covers a wide range of low and high-level events for invasion games. We release two multi-modal datasets comprising video and positional data with gold-standard annotations to foster research in fine-grained and ball-centered event spotting.
  arXiv  Detail & Related papers  (2021-08-25T10:09:28Z)
• 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)
• Generic Event Boundary Detection: A Benchmark for Event Segmentation [21.914662894860474]
  This paper presents a novel task together with a new benchmark for detecting generic, taxonomy-free event boundaries that segment a whole video into chunks. We introduce the task of Generic Event Boundary Detection (GEBD) and the new benchmark Kinetics-GEBD. Inspired by the cognitive finding that humans mark boundaries at points where they are unable to predict the future accurately, we explore un-supervised approaches.
  arXiv  Detail & Related papers  (2021-01-26T01:31:30Z)
• A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video [120.18562044084678]
  Abnormal event detection in video is a complex computer vision problem that has attracted significant attention in recent years. We propose a background-agnostic framework that learns from training videos containing only normal events.
  arXiv  Detail & Related papers  (2020-08-27T18:39:24Z)
• Team RUC_AIM3 Technical Report at Activitynet 2020 Task 2: Exploring Sequential Events Detection for Dense Video Captioning [63.91369308085091]
  We propose a novel and simple model for event sequence generation and explore temporal relationships of the event sequence in the video. The proposed model omits inefficient two-stage proposal generation and directly generates event boundaries conditioned on bi-directional temporal dependency in one pass. The overall system achieves state-of-the-art performance on the dense-captioning events in video task with 9.894 METEOR score on the challenge testing set.
  arXiv  Detail & Related papers  (2020-06-14T13:21:37Z)

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.