Saliency-Guided DETR for Moment Retrieval and Highlight Detection

• URL: http://arxiv.org/abs/2410.01615v1
• Date: Wed, 2 Oct 2024 14:53:45 GMT
• Title: Saliency-Guided DETR for Moment Retrieval and Highlight Detection
• Abstract summary: Existing approaches for video moment retrieval and highlight detection are not able to align text and video features efficiently. We propose a novel architecture that utilizes recent foundational video models designed for such alignment. For even better improvement, we developed InterVid-MR, a large-scale and high-quality dataset for pretraining.
• Score: 41.94295877935867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing approaches for video moment retrieval and highlight detection are not able to align text and video features efficiently, resulting in unsatisfying performance and limited production usage. To address this, we propose a novel architecture that utilizes recent foundational video models designed for such alignment. Combined with the introduced Saliency-Guided Cross Attention mechanism and a hybrid DETR architecture, our approach significantly enhances performance in both moment retrieval and highlight detection tasks. For even better improvement, we developed InterVid-MR, a large-scale and high-quality dataset for pretraining. Using it, our architecture achieves state-of-the-art results on the QVHighlights, Charades-STA and TACoS benchmarks. The proposed approach provides an efficient and scalable solution for both zero-shot and fine-tuning scenarios in video-language tasks.

Related papers

• Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence [2.512325213832099]
  Black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation.<n>Lack of fine-grained control and reliability presents significant challenges in professional video creation.<n>We introduce the Agentic Self-Improvement" framework, which reframes video into a closed-loop, goal-directed optimization.
  arXiv  Detail & Related papers  (2026-08-12T17:35:16Z)
• Q-Save: Towards Scoring and Attribution for Generated Video Evaluation [65.83319736145869]
  We present Q-Save, a new benchmark dataset and model for holistic evaluation of AI-generated video (AIGV) quality.<n>The dataset contains near 10000 videos, each annotated with a scalar mean opinion score (MOS) and fine-grained attribution labels.<n>We propose a unified evaluation model that jointly performs quality scoring and attribution-based explanation.
  arXiv  Detail & Related papers  (2025-11-24T07:00:21Z)
• Raccoon: Multi-stage Diffusion Training with Coarse-to-Fine Curating Videos [15.781862060265519]
  CFC-VIDS-1M is a high-quality video dataset constructed through a systematic coarse-to-fine curation pipeline. We develop RACCOON, a transformer-based architecture with decoupled spatial-temporal attention mechanisms.
  arXiv  Detail & Related papers  (2025-02-28T18:56:35Z)
• Understanding Long Videos via LLM-Powered Entity Relation Graphs [51.13422967711056]
  GraphVideoAgent is a framework that maps and monitors the evolving relationships between visual entities throughout the video sequence. Our approach demonstrates remarkable effectiveness when tested against industry benchmarks.
  arXiv  Detail & Related papers  (2025-01-27T10:57:24Z)
• VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval [8.908777234657046]
  Large-language and vision-language models (LLM/LVLMs) have gained prominence across various domains. Here we propose VideoLights, a novel HD/MR framework addressing these limitations through (i) Convolutional Projection and Feature Refinement modules. Comprehensive experiments on QVHighlights, TVSum, and Charades-STA benchmarks demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-02T14:45:53Z)
• Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling [96.64607294592062]
  Video Semantic Label Roleing (VidSRL) aims to detect salient events from given videos. Recent endeavors have put forth methods for VidSRL, but they can be subject to two key drawbacks.
  arXiv  Detail & Related papers  (2023-08-09T17:20:14Z)
• TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement [64.11385310305612]
  We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence. Our approach employs two stages: (1) a matching stage, which independently locates a suitable candidate point match for the query point on every other frame, and (2) a refinement stage, which updates both the trajectory and query features based on local correlations. The resulting model surpasses all baseline methods by a significant margin on the TAP-Vid benchmark, as demonstrated by an approximate 20% absolute average Jaccard (AJ) improvement on DAVIS.
  arXiv  Detail & Related papers  (2023-06-14T17:07:51Z)
• VS-Net: Multiscale Spatiotemporal Features for Lightweight Video Salient Document Detection [0.2578242050187029]
  We propose VS-Net, which captures multi-scaletemporal information with the help of dilated depth-wise separable convolution and Approximation Rank Pooling. Our model generates saliency maps considering both the background and foreground, making it perform better in challenging scenarios. The immense experiments regulated on the benchmark MIDV-500 dataset show that the VS-Net model outperforms state-of-the-art approaches in both time and robustness measures.
  arXiv  Detail & Related papers  (2023-01-11T13:07:31Z)
• AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism [64.70568612993416]
  We formulate a new task Livestream Highlight Detection, discuss and analyze the difficulties listed above and propose a novel architecture AntPivot to solve this problem. We construct a fully-annotated dataset AntHighlight to instantiate this task and evaluate the performance of our model.
  arXiv  Detail & Related papers  (2022-06-10T05:58:11Z)
• Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives [30.666823939595627]
  This paper reconsiders the multi-modal alignment problem in VideoQA from feature and sample perspectives. We adopt a heterogeneous graph architecture and design a hierarchical framework to align both trajectory-level and frame-level visual feature with language feature. Our method outperforms all the state-of-the-art models on the challenging NExT-QA benchmark.
  arXiv  Detail & Related papers  (2022-04-25T10:42:07Z)
• Target Adaptive Context Aggregation for Video Scene Graph Generation [36.669700084337045]
  This paper deals with a challenging task of video scene graph generation (VidSGG) We present a new em detect-to-track paradigm for this task by decoupling the context modeling for relation prediction from the complicated low-level entity tracking.
  arXiv  Detail & Related papers  (2021-08-18T12:46:28Z)
• Weakly Supervised Video Salient Object Detection [79.51227350937721]
  We present the first weakly supervised video salient object detection model based on relabeled "fixation guided scribble annotations" An "Appearance-motion fusion module" and bidirectional ConvLSTM based framework are proposed to achieve effective multi-modal learning and long-term temporal context modeling.
  arXiv  Detail & Related papers  (2021-04-06T09:48:38Z)
• Coherent Loss: A Generic Framework for Stable Video Segmentation [103.78087255807482]
  We investigate how a jittering artifact degrades the visual quality of video segmentation results. We propose a Coherent Loss with a generic framework to enhance the performance of a neural network against jittering artifacts.
  arXiv  Detail & Related papers  (2020-10-25T10:48:28Z)

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.