Related papers: Cross-view Action Recognition Understanding From E…
Action recognition is an important research topic in computer vision. It is the basic work for visual understanding and has been applied in many fields. Since human actions can vary in different environments, it is difficult to infer…
Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…
Egocentric activity recognition is one of the most challenging tasks in video analysis. It requires a fine-grained discrimination of small objects and their manipulation. While some methods base on strong supervision and attention…
Recent progress in legged locomotion has allowed highly dynamic and parkour-like behaviors for robots, similar to their biological counterparts. Yet, these methods mostly rely on egocentric (first-person) perception, limiting their…
The objective of this work is to learn an object-centric video representation, with the aim of improving transferability to novel tasks, i.e., tasks different from the pre-training task of action classification. To this end, we introduce a…
Ultra-long egocentric videos spanning multiple days present significant challenges for video understanding. Existing approaches still rely on fragmented local processing and limited temporal modeling, restricting their ability to reason…
Human action recognition has recently become one of the popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video…
Egocentric action anticipation is the task of predicting the future actions a camera wearer will likely perform based on past video observations. While in a real-world system it is fundamental to output such predictions before the action…
Standard methods for video recognition use large CNNs designed to capture spatio-temporal data. However, training these models requires a large amount of labeled training data, containing a wide variety of actions, scenes, settings and…
In Composed Video Retrieval, a video and a textual description which modifies the video content are provided as inputs to the model. The aim is to retrieve the relevant video with the modified content from a database of videos. In this…
First-person video highlights a camera-wearer's activities in the context of their persistent environment. However, current video understanding approaches reason over visual features from short video clips that are detached from the…
Egocentric videos are characterised by their ability to have the first person view. With the popularity of Google Glass and GoPro, use of egocentric videos is on the rise. Recognizing action of the wearer from egocentric videos is an…
Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited availability of egocentric training data and its inherent partial observability of humans'…
This paper addresses the daily challenges encountered by visually impaired individuals, such as limited access to information, navigation difficulties, and barriers to social interaction. To alleviate these challenges, we introduce a novel…
Egocentric human videos provide a scalable source of manipulation demonstrations; however, deploying them on robots requires active viewpoint control to maintain task-critical visibility, which human viewpoint imitation often fails to…
We introduce FEEL (Force-Enhanced Egocentric Learning), the first large-scale dataset pairing force measurements gathered from custom piezoresistive gloves with egocentric video. Our gloves enable scalable data collection, and FEEL contains…
Non-verbal communication plays a particularly important role in a wide range of scenarios in Human-Robot Interaction (HRI). Accordingly, this work addresses the problem of human gesture recognition. In particular, we focus on head and eye…
We study the domain adaptation task for action recognition, namely domain adaptive action recognition, which aims to effectively transfer action recognition power from a label-sufficient source domain to a label-free target domain. Since…
Vision Language Models (VLMs) have achieved strong performance across diverse video understanding tasks. However, their viewpoint invariant training limits their ability to understand egocentric properties (e.g., human object interactions)…
In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the…