Vision transformers are emerging as a powerful tool to solve computer vision problems.
Recent techniques have also proven the efficacy of transformers beyond the image domain …

Most state-of-the-art methods for action segmentation are based on single input modalities
or naive fusion of multiple data sources. However, effective fusion of complementary …

The portrait matting task aims to extract an alpha matte with complete semantics and finely
detailed contours. In comparison to CNN-based approaches transformers with self-attention …

Weakly-supervised action segmentation is a task of learning to partition a long video into
several action segments where training videos are only accompanied by transcripts …

Temporal action segmentation (TAS) of minute-long untrimmed videos involves locating and
classifying human action segments using multiple action class labels. Previously, research …

Action segmentation is a research hotspot in human action analysis, which aims to split
videos into segments of different actions. Recent algorithms have achieved great success in …

Streaming neural network models for fast frame-wise responses to various speech and
sensory signals are widely adopted on resource-constrained platforms. Hence, increasing …

Online action detection aims at the accurate action prediction of the current frame based on
long historical observations. Meanwhile, it demands real-time inference on online streaming …

Action segmentation is an emerging task in video understanding, particularly for untrimmed
videos containing multiple actions. However, existing video-based methods may struggle …

Streaming neural network models for fast frame-wise responses to various speech and
sensory signals are widely adopted on resource-constrained platforms. Hence, increasing …