Humans drive in a holistic fashion which entails, in particular, understanding dynamic road
events and their evolution. Injecting these capabilities in autonomous vehicles can thus take …

The goal of this paper is to detect the spatio-temporal extent of an action. The two-stream
detection network based on RGB and flow provides state-of-the-art accuracy at the expense …

Spatio-temporal action detection (STAD) aims to classify the actions present in a video and
localize them in space and time. It has become a particularly active area of research in …

Current methods for spatiotemporal action tube detection often extend a bounding box
proposal at a given key-frame into a 3D temporal cuboid and pool features from nearby …

Despite the recent advances in video classification, progress in spatio-temporal action
recognition has lagged behind. A major contributing factor has been the prohibitive cost of …

Spatial and temporal action detection aims to precisely locate actions while predicting their
respective categories. The existing solution, TubeR (Zhao et al., 2022), is designed to …

We propose a novel domain adaptive action detection approach and a new adaptation
protocol that leverages the recent advancements in image-level unsupervised domain …

Dynamic scene understanding is the ability of a computer system to interpret and make
sense of the visual information present in a video of a real-world scene. In this thesis, we …

Interactive autonomous applications require robustness of the perception engine to artifacts
in unconstrained videos. In this paper, we examine the effect of camera motion on the task of …

The goal of this work is spatio-temporal action localization in videos, using only the
supervision from video-level class labels. The state-of-the-art casts this weakly-supervised …