Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos
Temporal action localization is a recently-emerging task, aiming to localize video segments from untrimmed videos that contain specific actions. Despite the remarkable recent progress, most two-stage action localization methods still suffer from imprecise temporal boundaries of action proposals. This work proposes a novel integrated temporal scale aggregation network (TSA-Net). Our main insight is that ensembling convolution filters with different dilation rates can effectively enlarge the receptive field with low computational cost, which inspires us to devise multi-dilation temporal convolution (MDC) block. Furthermore, to tackle video action instances with different durations, TSA-Net consists of multiple branches of sub-networks. Each of them adopts stacked MDC blocks with different dilation parameters, accomplishing a temporal receptive field specially optimized for specific-duration actions. We follow the formulation of boundary point detection, novelly detecting three kinds of critical points (ie, starting / mid-point / ending) and pairing them for proposal generation. Comprehensive evaluations are conducted on two challenging video benchmarks, THUMOS14 and ActivityNet-1.3. Our proposed TSA-Net demonstrates clear and consistent better performances and re-calibrates new state-of-the-art on both benchmarks. For example, our new record on THUMOS14 is 46.9% while the previous best is 42.8% under mAP@0.5.
Code (0)
등록된 구현이 없습니다.
Tasks
Action LocalizationTemporal Action LocalizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Time Matters: Multi-scale Temporalization of Social Media Popularity
The evolution of social media popularity exhibits rich temporality, i.e., popularities change over time at various levels of temporal granularity. This is influenced by temporal variations of public attentions or user ac…
Social Media Popularity PredictionTemporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition
Speech emotion recognition (SER) plays a vital role in improving the interactions between humans and machines by inferring human emotion and affective states from speech signals. Whereas recent works primarily focus on m…
Speech Emotion RecognitionMotion-Guided Global-Local Aggregation Transformer Network for Precipitation Nowcasting
Nowadays deep learning-based weather radar echo extrapolation methods have competently improved nowcasting quality. Current pure convolutional or convolutional recurrent neural network-based extrapolation pipelines inher…
Optical Flow EstimationWhich Leakage Types Matter? A Quantitative Landscape Across 2,047 Benchmark Datasets
Twenty-eight within-subject counterfactual experiments across 2,047 iid tabular datasets, plus a boundary experiment on 129 temporal datasets, measure the severity of four data leakage classes in machine learning. Class …
LIFL: A Lightweight, Event-driven Serverless Platform for Federated Learning
Federated Learning (FL) typically involves a large-scale, distributed system with individual user devices/servers training models locally and then aggregating their model updates on a trusted central server. Existing sys…
Federated LearningManagement