paper-with-me

Papers

A Context-Aware Loss Function for Action Spotting in Soccer Videos

2019-12-03 · CVPR 2020 6 · Anthony Cioppa, Adrien Deliège, Silvio Giancola, Bernard Ghanem, Marc Van Droogenbroeck, Rikke Gade, Thomas B. Moeslund

In video understanding, action spotting consists in temporally localizing human-induced events annotated with single timestamps. In this paper, we propose a novel loss function that specifically considers the temporal context naturally present around each action, rather than focusing on the single annotated frame to spot. We benchmark our loss on a large dataset of soccer videos, SoccerNet, and achieve an improvement of 12.8% over the baseline. We show the generalization capability of our loss for generic activity proposals and detection on ActivityNet, by spotting the beginning and the end of each activity. Furthermore, we provide an extended ablation study and display challenging cases for action spotting in soccer videos. Finally, we qualitatively illustrate how our loss induces a precise temporal understanding of actions and show how such semantic knowledge can be used for automatic highlights generation.

📄 PDF Abstract BibTeX arXiv:1912.01326

Code (1)

cioppaanthony/context-aware-loss 공식 구현 tf

Tasks

Action SpottingVideo Understanding

Similar Papers 제목 키워드 기반

SMART: MLLM-guided Temporal Alignment for Unifying Sign Language Recognition and Spotting

2026-08-26 · Eunjee Choi, JungHoon Sung, Seongwhan Cho, Chu Xin 외 arxiv

Continuous sign language recognition (CSLR) aims to recognize gloss sequences from unsegmented sign videos under weak sequence-level supervision. However, existing methods rely on sentence-level gloss annotations, provid…

Sign Language RecognitionRepresentation Learning

Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts

2021-04-14 · Silvio Giancola, Bernard Ghanem

Toward the goal of automatic production for sports broadcasts, a paramount task consists in understanding the high-level semantic information of the game in play. For instance, recognizing and localizing the main actions…

Action Spotting

Sign Spotting Disambiguation using Large Language Models

2025-07-04 · JianHe Low, Ozge Mercanoglu Sincan, Richard Bowden arxiv

Sign spotting, the task of identifying and localizing individual signs within continuous sign language video, plays a pivotal role in scaling dataset annotations and addressing the severe data scarcity issue in sign lang…

Sign Language Translation

Prototypical Metric Transfer Learning for Continuous Speech Keyword Spotting With Limited Training Data

2019-01-12 · Harshita Seth, Pulkit Kumar, Muktabh Mayank Srivastava

Continuous Speech Keyword Spotting (CSKS) is the problem of spotting keywords in recorded conversations, when a small number of instances of keywords are available in training data. Unlike the more common Keyword Spottin…

General Classificationimbalanced classificationKeyword SpottingTransfer Learning

GLASS: Global to Local Attention for Scene-Text Spotting

2022-08-05 · Roi Ronen, Shahar Tsiper, Oron Anschel, Inbal Lavi 외

In recent years, the dominant paradigm for text spotting is to combine the tasks of text detection and recognition into a single end-to-end framework. Under this paradigm, both tasks are accomplished by operating over a …

Text DetectionText Spotting