TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Cascaded Boundary Regression for Temporal Action Detection

Cascaded Boundary Regression for Temporal Action Detection

Jiyang Gao, Zhenheng Yang, Ram Nevatia

2017-05-02Action Detectionregression
PaperPDF

Abstract

Temporal action detection in long videos is an important problem. State-of-the-art methods address this problem by applying action classifiers on sliding windows. Although sliding windows may contain an identifiable portion of the actions, they may not necessarily cover the entire action instance, which would lead to inferior performance. We adapt a two-stage temporal action detection pipeline with Cascaded Boundary Regression (CBR) model. Class-agnostic proposals and specific actions are detected respectively in the first and the second stage. CBR uses temporal coordinate regression to refine the temporal boundaries of the sliding windows. The salient aspect of the refinement process is that, inside each stage, the temporal boundaries are adjusted in a cascaded way by feeding the refined windows back to the system for further boundary refinement. We test CBR on THUMOS-14 and TVSeries, and achieve state-of-the-art performance on both datasets. The performance gain is especially remarkable under high IoU thresholds, e.g. map@tIoU=0.5 on THUMOS-14 is improved from 19.0% to 31.0%.

Results

TaskDatasetMetricValueModel
VideoTHUMOS’14mAP IOU@0.160.1CBR-TS
VideoTHUMOS’14mAP IOU@0.256.7CBR-TS
VideoTHUMOS’14mAP IOU@0.350.1CBR-TS
VideoTHUMOS’14mAP IOU@0.441.3CBR-TS
VideoTHUMOS’14mAP IOU@0.531CBR-TS
VideoTHUMOS’14mAP IOU@0.619.1CBR-TS
VideoTHUMOS’14mAP IOU@0.79.9CBR-TS
Temporal Action LocalizationTHUMOS’14mAP IOU@0.160.1CBR-TS
Temporal Action LocalizationTHUMOS’14mAP IOU@0.256.7CBR-TS
Temporal Action LocalizationTHUMOS’14mAP IOU@0.350.1CBR-TS
Temporal Action LocalizationTHUMOS’14mAP IOU@0.441.3CBR-TS
Temporal Action LocalizationTHUMOS’14mAP IOU@0.531CBR-TS
Temporal Action LocalizationTHUMOS’14mAP IOU@0.619.1CBR-TS
Temporal Action LocalizationTHUMOS’14mAP IOU@0.79.9CBR-TS
Zero-Shot LearningTHUMOS’14mAP IOU@0.160.1CBR-TS
Zero-Shot LearningTHUMOS’14mAP IOU@0.256.7CBR-TS
Zero-Shot LearningTHUMOS’14mAP IOU@0.350.1CBR-TS
Zero-Shot LearningTHUMOS’14mAP IOU@0.441.3CBR-TS
Zero-Shot LearningTHUMOS’14mAP IOU@0.531CBR-TS
Zero-Shot LearningTHUMOS’14mAP IOU@0.619.1CBR-TS
Zero-Shot LearningTHUMOS’14mAP IOU@0.79.9CBR-TS
Action LocalizationTHUMOS’14mAP IOU@0.160.1CBR-TS
Action LocalizationTHUMOS’14mAP IOU@0.256.7CBR-TS
Action LocalizationTHUMOS’14mAP IOU@0.350.1CBR-TS
Action LocalizationTHUMOS’14mAP IOU@0.441.3CBR-TS
Action LocalizationTHUMOS’14mAP IOU@0.531CBR-TS
Action LocalizationTHUMOS’14mAP IOU@0.619.1CBR-TS
Action LocalizationTHUMOS’14mAP IOU@0.79.9CBR-TS

Related Papers

Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression2025-07-20Neural Network-Guided Symbolic Regression for Interpretable Descriptor Discovery in Perovskite Catalysts2025-07-16Imbalanced Regression Pipeline Recommendation2025-07-16Second-Order Bounds for [0,1]-Valued Regression via Betting Loss2025-07-16Sparse Regression Codes exploit Multi-User Diversity without CSI2025-07-15Bradley-Terry and Multi-Objective Reward Modeling Are Complementary2025-07-10Active Learning for Manifold Gaussian Process Regression2025-06-26CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment2025-06-25