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 …

Generating multi-sentence descriptions for video is considered to be the most complex task
in computer vision and natural language understanding due to the intricate nature of video …

Action detection is an essential and challenging task, especially for densely labelled
datasets of untrimmed videos. The temporal relation is complex in those datasets, including …

We introduce the task of spotting temporally precise, fine-grained events in video (detecting
the precise moment in time events occur). Precise spotting requires models to reason …

Abstract We propose Token Turing Machines (TTM), a sequential, autoregressive
Transformer model with memory for real-world sequential visual understanding. Our model …

In video understanding, most cross-modal knowledge distillation (KD) methods are tailored
for classification tasks, focusing on the discriminative representation of the trimmed videos …

Skeleton-based action segmentation requires recognizing composable actions in untrimmed
videos. Current approaches decouple this problem by first extracting local visual features …

Traditional temporal action detection (TAD) usually handles untrimmed videos with small
number of action instances from a single label (eg, ActivityNet, THUMOS). However, this …

Temporal Action Localization (TAL) is a challenging task in video understanding that aims to
identify and localize actions within a video sequence. Recent studies have emphasized the …

We present PAT, a transformer-based network that learns complex temporal co-occurrence
action dependencies in a video by exploiting multi-scale temporal features. In existing …