相关论文: X-MIC: Cross-Modal Instance Conditioning for Egoce…
Automatically describing video, or video captioning, has been widely studied in the multimedia field. This paper proposes a new task of sensor-augmented egocentric-video captioning, a newly constructed dataset for it called MMAC Captions,…
Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., ViT) are following the same trend, achieving the best…
Recent advancements in Multimodal Large Language Models (MLLMs) have revolutionized the field of vision-language understanding by integrating visual perception capabilities into Large Language Models (LLMs). The prevailing trend in this…
The scale and diversity of demonstration data required for imitation learning is a significant challenge. We present EgoMimic, a full-stack framework which scales manipulation via human embodiment data, specifically egocentric human videos…
Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video…
Most existing vision-language pre-training (VLP) approaches adopt cross-modal masked language modeling (CMLM) to learn vision-language associations. However, we find that CMLM is insufficient for this purpose according to our observations:…
Egocentric video-language understanding demands both high efficiency and accurate spatial-temporal modeling. Existing approaches face three key challenges: 1) Excessive pre-training cost arising from multi-stage pre-training pipelines, 2)…
Analyzing instructional interactions between an instructor and a learner who are co-present in the same physical space is a critical problem for educational support and skill transfer. Yet such face-to-face instructional scenes have not…
Long-form egocentric video understanding provides rich contextual information and unique insights into long-term human behaviors, holding significant potential for applications in embodied intelligence, long-term activity analysis, and…
We present Video-LLaMA a multi-modal framework that empowers Large Language Models (LLMs) with the capability of understanding both visual and auditory content in the video. Video-LLaMA bootstraps cross-modal training from the frozen…
Multi-domain task-incremental learning requires a model to sequentially acquire knowledge across visually diverse domains without forgetting prior tasks, and without access to task identity at inference. Parameter-efficient methods built on…
Spatiotemporal video grounding aims to localize target entities in videos based on textual queries. While existing research has made significant progress in exocentric videos, the egocentric setting remains relatively underexplored, despite…
Scaling general-purpose manipulation to new robot embodiments remains challenging: each platform typically needs large, homogeneous demonstrations, and end-to-end pixel-to-action pipelines may degenerate under background and viewpoint…
We present Vinci, a vision-language system designed to provide real-time, comprehensive AI assistance on portable devices. At its core, Vinci leverages EgoVideo-VL, a novel model that integrates an egocentric vision foundation model with a…
Pretraining egocentric vision-language models has become essential to improving downstream egocentric video-text tasks. These egocentric foundation models commonly use the transformer architecture. The memory footprint of these models…
Human actions in egocentric videos are often hand-object interactions composed from a verb (performed by the hand) applied to an object. Despite their extensive scaling up, egocentric datasets still face two limitations - sparsity of action…
Most transformer-based video encoders are limited to short temporal contexts due to their quadratic complexity. While various attempts have been made to extend this context, this has often come at the cost of both conceptual and…
Egocentric videos capture scenes from a wearer's viewpoint, resulting in dynamic backgrounds, frequent motion, and occlusions, posing challenges to accurate keystep recognition. We propose a flexible graph-learning framework for…
Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research suggests current vision-language models (VLMs) trained on curated…
We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios. We propose a simple yet effective…