Three Birds with One Stone: Multi-Task Temporal Action Detection via Recycling Temporal Annotations
Temporal action detection on unconstrained videos has seen significant research progress in recent years. Deep learning has achieved enormous success in this direction. However, collecting large-scale temporal detection datasets to ensuring promising performance in the real-world is a laborious, impractical and time consuming process. Accordingly, we present a novel improved temporal action localization model that is better able to take advantage of limited labeled data available. Specifically, we design two auxiliary tasks by reconstructing the available label information and then facilitate the learning of the temporal action detection model. Each task generates their supervision signal by recycling the original annotations, and are jointly trained with the temporal action detection model in a multi-task learning fashion. Note that the proposed approach can be pluggable to any region proposal based temporal action detection models. We conduct extensive experiments on three benchmark datasets, namely THUMOS'14, Charades and ActivityNet. Our experimental results confirm the effectiveness of the proposed model.
Code (0)
등록된 구현이 없습니다.
Tasks
Action DetectionAction LocalizationMulti-Task LearningRegion ProposalTemporal Action LocalizationSimilar Papers 제목 키워드 기반
ECNU: One Stone Two Birds: Ensemble of Heterogenous Measures for Semantic Relatedness and Textual Entailment
Transduction with Matrix Completion: Three Birds with One Stone
We pose transductive classification as a matrix completion problem. By assuming the underlying matrix has a low rank, our formulation is able to handle three problems simultaneously: i) multi-label learning, where each i…
General ClassificationMatrix CompletionMulti-Label LearningOne Stone, Three Birds: Self-adaptive Optimal Transport for Multi-VLM Selection, Adaptation, and Ensembling
Vision-language models (VLMs) enable visual recognition from semantic class descriptions, which makes them attractive when target annotations are scarce or unavailable. Most deployment pipelines, however, first choose a …
Automatic recognition of element classes and boundaries in the birdsong with variable sequences
Researches on sequential vocalization often require analysis of vocalizations in long continuous sounds. In such studies as developmental ones or studies across generations in which days or months of vocalizations must b…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Boundary DetectionGeneral Classification+2Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
In this paper, we aim at solving pixel-wise binary problems, including salient object segmentation, skeleton extraction, and edge detection, by introducing a unified architecture. Previous works have proposed tailored me…
Edge DetectionSemantic Segmentation