Related papers: EgoDistill: Egocentric Head Motion Distillation fo…

Generating long, coherent egocentric videos is difficult, as hand-object interactions and procedural tasks require reliable long-term memory. Existing autoregressive models suffer from content drift, where object identity and scene…

Environment understanding in egocentric videos is an important step for applications like robotics, augmented reality and assistive technologies. These videos are characterized by dynamic interactions and a strong dependence on the wearer…

Egocentric videos provide valuable insights into human interactions with the physical world, which has sparked growing interest in the computer vision and robotics communities. A critical challenge in fully understanding the geometry and…

Egocentric videos offer fine-grained information for high-fidelity modeling of human behaviors. Hands and interacting objects are one crucial aspect of understanding a viewer's behaviors and intentions. We provide a labeled dataset…

Dataset distillation aims to synthesize a small dataset from a large dataset, enabling the model trained on it to perform well on the original dataset. With the blooming of large language models and multimodal large language models, the…

Human activities are inherently complex, often involving numerous object interactions. To better understand these activities, it is crucial to model their interactions with the environment captured through dynamic changes. The recent…

Affective computing with Electroencephalogram (EEG) is a challenging task that requires cumbersome models to effectively learn the information contained in large-scale EEG signals, causing difficulties for real-time smart-device deployment.…

Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over conventional cameras. A hurdle of training event-based models is the lack of large…

Different video understanding tasks are typically treated in isolation, and even with distinct types of curated data (e.g., classifying sports in one dataset, tracking animals in another). However, in wearable cameras, the immersive…

Dataset distillation aims to distill the knowledge of a large-scale real dataset into small yet informative synthetic data such that a model trained on it performs as well as a model trained on the full dataset. Despite recent progress,…

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…

In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for the EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge. Especially, we exploit the recently released Ego4D dataset…

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however,…

Dataset distillation has demonstrated remarkable effectiveness in high-compression scenarios for image datasets. While video datasets inherently contain greater redundancy, existing video dataset distillation methods primarily focus on…

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…

With recent advances in embodied agents and AR devices, egocentric observations are readily available as input for real-world interactive online applications. However, egocentric viewpoints can only sporadically observe hands, in addition…

Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained…

Recent weakly-supervised methods for scene flow estimation from LiDAR point clouds are limited to explicit reasoning on object-level. These methods perform multiple iterative optimizations for each rigid object, which makes them vulnerable…

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…

Distilled video generation models offer fast and efficient synthesis but struggle with motion customization when guided by reference videos, especially under training-free settings. Existing training-free methods, originally designed for…