TVNet: Temporal Voting Network for Action Localization
We propose a Temporal Voting Network (TVNet) for action localization in untrimmed videos. This incorporates a novel Voting Evidence Module to locate temporal boundaries, more accurately, where temporal contextual evidence is accumulated to predict frame-level probabilities of start and end action boundaries. Our action-independent evidence module is incorporated within a pipeline to calculate confidence scores and action classes. We achieve an average mAP of 34.6% on ActivityNet-1.3, particularly outperforming previous methods with the highest IoU of 0.95. TVNet also achieves mAP of 56.0% when combined with PGCN and 59.1% with MUSES at 0.5 IoU on THUMOS14 and outperforms prior work at all thresholds. Our code is available at https://github.com/hanielwang/TVNet.
Code (1)
Tasks
Action LocalizationSimilar Papers 제목 키워드 기반
End-to-End Learning of Motion Representation for Video Understanding
Despite the recent success of end-to-end learned representations, hand-crafted optical flow features are still widely used in video analysis tasks. To fill this gap, we propose TVNet, a novel end-to-end trainable neural …
Action RecognitionOptical Flow EstimationVideo UnderstandingMS-TVNet:A Long-Term Time Series Prediction Method Based on Multi-Scale Dynamic Convolution
Long-term time series prediction has predominantly relied on Transformer and MLP models, while the potential of convolutional networks in this domain remains underexplored. To address this gap, we introduce a novel multi…
Time SeriesTime Series PredictionMTVNet: Mapping using Transformers for Volumes -- Network for Super-Resolution with Long-Range Interactions
Until now, it has been difficult for volumetric super-resolution to utilize the recent advances in transformer-based models seen in 2D super-resolution. The memory required for self-attention in 3D volumes limits the rec…
Super-ResolutionCAR-BRAINet: Sub-6GHz Aided Spatial Adaptive Beam Prediction with Multi Head Attention for Heterogeneous Vehicular Networks
Heterogeneous Vehicular Networks (HetVNets) play a key role by stacking different communication technologies such as sub-6GHz, mm-wave and DSRC to meet diverse connectivity needs of 5G/B5G vehicular networks. HetVNet hel…
Beam PredictionAdaptive Unfolding Total Variation Network for Low-Light Image Enhancement
Real-world low-light images suffer from two main degradations, namely, inevitable noise and poor visibility. Since the noise exhibits different levels, its estimation has been implemented in recent works when enhancing l…
DenoisingImage EnhancementLow-Light Image EnhancementNoise Estimation+1