Related papers: Egocentric Action Recognition by Video Attention a…
This technical report presents our solution, EgoAdapt (Egocentric Adaptation via Category, Calibration, and Consistency), to the CVPR 2026 HD-EPIC VQA challenge. HD-EPIC evaluates whether a vision-language model can reason over realistic…
Video action detection (VAD) aims to detect actors and classify their actions in a video. We figure that VAD suffers more from classification rather than localization of actors. Hence, we analyze how prevailing methods form features for…
Recognizing human activities from visual inputs, particularly through a first-person viewpoint, is essential for enabling robots to replicate human behavior. Egocentric vision, characterized by cameras worn by observers, captures diverse…
In this paper we consider the problem of classifying fine-grained, multi-step activities (e.g., cooking different recipes, making disparate home improvements, creating various forms of arts and crafts) from long videos spanning up to…
Short-term action anticipation (STA) in first-person videos is a challenging task that involves understanding the next active object interactions and predicting future actions. Existing action anticipation methods have primarily focused on…
Monitoring the progression of an action towards completion offers fine grained insight into the actor's behaviour. In this work, we target detecting the completion moment of actions, that is the moment when the action's goal has been…
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…
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 remarkable…
Videos are more well-organized curated data sources for visual concept learning than images. Unlike the 2-dimensional images which only involve the spatial information, the additional temporal dimension bridges and synchronizes multiple…
Despite the notable progress made in action recognition tasks, not much work has been done in action recognition specifically for human-robot interaction. In this paper, we deeply explore the characteristics of the action recognition task…
In this paper, we address the challenging problem of action recognition, using event-based cameras. To recognise most gestural actions, often higher temporal precision is required for sampling visual information. Actions are defined by…
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,…
We propose an action parsing algorithm to parse a video sequence containing an unknown number of actions into its action segments. We argue that context information, particularly the temporal information about other actions in the video…
We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we…
Vision-Language Models (VLMs) have demonstrated impressive capabilities in zero-shot action recognition by learning to associate video embeddings with class embeddings. However, a significant challenge arises when relying solely on action…
We present our solution to the BinEgo-360 Challenge at ICCV 2025, which focuses on temporal action localization (TAL) in multi-perspective and multi-modal video settings. The challenge provides a dataset containing panoramic, third-person,…
Understanding instructional videos requires recognizing fine-grained actions and modeling their temporal relations, which remains challenging for current Video Foundation Models (VFMs). This difficulty stems from noisy web supervision and a…
Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility. This paper introduces a novel approach to instance segmentation and tracking in…
Temporal action segmentation classifies the action of each frame in (long) video sequences. Due to the high cost of frame-wise labeling, we propose the first semi-supervised method for temporal action segmentation. Our method hinges on…
We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio…