相关论文: EgoViT: Pyramid Video Transformer for Egocentric A…
Understanding and predicting object motion from egocentric video is fundamental to embodied perception and interaction. However, generating physically consistent 6DoF trajectories remains challenging due to occlusions, fast motion, and the…
Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor…
Egocentric vision captures the scene from the point of view of the camera wearer, while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is crucial to developing next-generation AI agents. The…
We introduce Activity Graph Transformer, an end-to-end learnable model for temporal action localization, that receives a video as input and directly predicts a set of action instances that appear in the video. Detecting and localizing…
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…
The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we…
Ensuring safety in autonomous driving is a complex challenge requiring handling unknown objects and unforeseen driving scenarios. We develop multiscale video transformers capable of detecting unknown objects using only motion cues. Video…
Understanding human behavior from complementary egocentric (ego) and exocentric (exo) points of view enables the development of systems that can support workers in industrial environments and enhance their safety. However, progress in this…
Human comprehension of a video stream is naturally broad: in a few instants, we are able to understand what is happening, the relevance and relationship of objects, and forecast what will follow in the near future, everything all at once.…
The Transformer architecture has gained significant popularity in computer vision tasks due to its capacity to generalize and capture long-range dependencies. This characteristic makes it well-suited for generating spatiotemporal tokens…
Procedural activities are sequences of key-steps aimed at achieving specific goals. They are crucial to build intelligent agents able to assist users effectively. In this context, task graphs have emerged as a human-understandable…
Lately, there has been growing interest in adapting vision-language models (VLMs) to image and third-person video classification due to their success in zero-shot recognition. However, the adaptation of these models to egocentric videos has…
Deep convolutional networks are widely used in video action recognition. 3D convolutions are one prominent approach to deal with the additional time dimension. While 3D convolutions typically lead to higher accuracies, the inner workings of…
Efficient video action recognition remains a challenging problem. One large model after another takes the place of the state-of-the-art on the Kinetics dataset, but real-world efficiency evaluations are often lacking. In this work, we fill…
The event camera's low power consumption and ability to capture microsecond brightness changes make it attractive for various computer vision tasks. Existing event representation methods typically convert events into frames, voxel grids, or…
Interactive object understanding, or what we can do to objects and how is a long-standing goal of computer vision. In this paper, we tackle this problem through observation of human hands in in-the-wild egocentric videos. We demonstrate…
Controllable and physically grounded egocentric video generation is essential for embodied agents to reason about how their own and others' actions manifest and change the world. Compared to generic video synthesis, egocentric generation is…
We present Ego-1K, a large-scale collection of time-synchronized egocentric multiview videos designed to advance neural 3D video synthesis and dynamic scene understanding. The dataset contains nearly 1,000 short egocentric videos captured…
In this paper we propose a new framework to categorize social interactions in egocentric videos, we named InteractionGCN. Our method extracts patterns of relational and non-relational cues at the frame level and uses them to build a…
Recent advances in egocentric video understanding models are promising, but their heavy computational expense is a barrier for many real-world applications. To address this challenge, we propose EgoDistill, a distillation-based approach…