Related papers: Spatio-Temporal Context Prompting for Zero-Shot Ac…
We introduce the task of weakly supervised learning for detecting human and object interactions in videos. Our task poses unique challenges as a system does not know what types of human-object interactions are present in a video or the…
Temporal Action Detection and Moment Retrieval constitute two pivotal tasks in video understanding, focusing on precisely localizing temporal segments corresponding to specific actions or events. Recent advancements introduced Moment…
In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and…
Understanding crowd behavior in video is challenging for computer vision. There have been increasing attempts on modeling crowded scenes by introducing ever larger property ontologies (attributes) and annotating ever larger training…
Driven by large-scale contrastive vision-language pre-trained models such as CLIP, recent advancements in the image-text matching task have achieved remarkable success in representation learning. Due to image-level visual-language…
Temporal Activity Detection aims to predict activity classes per frame, in contrast to video-level predictions in Activity Classification (i.e., Activity Recognition). Due to the expensive frame-level annotations required for detection, the…
This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based…
In this paper, we address the problem of searching action proposals in unconstrained video clips. Our approach starts from actionness estimation on frame-level bounding boxes, and then aggregates the bounding boxes belonging to the same…
Learning to infer labels in an open world, i.e., in an environment where the target ``labels'' are unknown, is an important characteristic for achieving autonomy. Foundation models, pre-trained on enormous amounts of data, have shown…
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never…
The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to…
Video anomaly detection aims to discover abnormal events in videos, and the principal objects are target objects such as people and vehicles. Each target in the video data has rich spatio-temporal context information. Most existing methods…
We describe a latent approach that learns to detect actions in long sequences given training videos with only whole-video class labels. Our approach makes use of two innovations to attention-modeling in weakly-supervised learning. First,…
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an…
Action recognition and detection in the context of long untrimmed video sequences has seen an increased attention from the research community. However, annotation of complex activities is usually time consuming and challenging in practice.…
Tactile signals collected by wearable electronics are essential in modeling and understanding human behavior. One of the main applications of tactile signals is action classification, especially in healthcare and robotics. However, existing…
Visual saliency, which predicts regions in the field of view that draw the most visual attention, has attracted a lot of interest from researchers. It has already been used in several vision tasks, e.g., image classification, object…
Action recognition is a critical task in video understanding, requiring the comprehensive capture of spatio-temporal cues across various scales. However, existing methods often overlook the multi-granularity nature of actions. To address…
We present a method to accelerate global illumination computation in dynamic environments by taking advantage of limitations of the human visual system. A model of visual attention is used to locate regions of interest in a scene and to…
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion…