Related papers: R-Clustering for Egocentric Video Segmentation
With rich temporal-spatial information, video-based person re-identification methods have shown broad prospects. Although tracklets can be easily obtained with ready-made tracking models, annotating identities is still expensive and…
Due to the high cost of data annotation in supervised learning for person re-identification (Re-ID) methods, unsupervised learning becomes more attractive in the real world. The Bottom-up Clustering (BUC) approach based on hierarchical…
Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information…
The possibility of sharing one's point of view makes use of wearable cameras compelling. These videos are often long, boring and coupled with extreme shake, as the camera is worn on a moving person. Fast forwarding (i.e. frame sampling) is…
Segmentation from point cloud data is essential in many applications such as remote sensing, mobile robots, or autonomous cars. However, the point clouds captured by the 3D range sensor are commonly sparse and unstructured, challenging…
We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and temporal consistency of segmentation masks across video frames. The…
In this paper, we propose a \textbf{Tr}ansformer-based RGB-D \textbf{e}gocentric \textbf{a}ction \textbf{r}ecognition framework, called Trear. It consists of two modules, inter-frame attention encoder and mutual-attentional fusion block.…
Real-time video analytics systems typically place models with fewer weights on edge devices to reduce latency. The distribution of video content features may change over time for various reasons (i.e. light and weather change) , leading to…
We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects. Unlike previous solutions relying on batch input or imposing priors on scene structure…
We introduce EgoPoints, a benchmark for point tracking in egocentric videos. We annotate 4.7K challenging tracks in egocentric sequences. Compared to the popular TAP-Vid-DAVIS evaluation benchmark, we include 9x more points that go…
Egocentric video is increasingly used as a data source for robot learning, activity understanding, and embodied AI research, but collecting it at scale remains fragmented in practice: each candidate host device, such as an Android phone,…
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion},…
We present an approach for identifying picturesque highlights from large amounts of egocentric video data. Given a set of egocentric videos captured over the course of a vacation, our method analyzes the videos and looks for images that…
Face clustering is an essential tool for exploiting the unlabeled face data, and has a wide range of applications including face annotation and retrieval. Recent works show that supervised clustering can result in noticeable performance…
Unsupervised image classification, or image clustering, aims to group unlabeled images into semantically meaningful categories. Early methods integrated representation learning and clustering within an iterative framework. However, the rise…
Video co-segmentation refers to the task of jointly segmenting common objects appearing in a given group of videos. In practice, high-dimensional data such as videos can be conceptually thought as being drawn from a union of subspaces…
Tracking of motion objects in the surveillance videos is useful for the monitoring and analysis. The performance of the surveillance system will deteriorate when shadows are detected as moving objects. Therefore, shadow detection and…
Anticipating human actions is an important task that needs to be addressed for the development of reliable intelligent agents, such as self-driving cars or robot assistants. While the ability to make future predictions with high accuracy is…
The widespread deployment of smartphones and location-enabled, networked in-vehicle devices renders it increasingly feasible to collect streaming trajectory data of moving objects. The continuous clustering of such data can enable a variety…
Identifying new user intents is an essential task in the dialogue system. However, it is hard to get satisfying clustering results since the definition of intents is strongly guided by prior knowledge. Existing methods incorporate prior…