English
Related papers

Related papers: Omnivore: A Single Model for Many Visual Modalitie…

200 papers

Conventional Vision Transformer simplifies visual modeling by standardizing input resolutions, often disregarding the variability of natural visual data and compromising spatial-contextual fidelity. While preliminary explorations have…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Limeng Qiao , Yiyang Gan , Bairui Wang , Jie Qin , Shuang Xu , Siqi Yang , Lin Ma

Prior approaches injecting camera control into diffusion models have focused on specific subsets of 4D consistency tasks: novel view synthesis, text-to-video with camera control, image-to-video, amongst others. Therefore, these fragmented…

Computer Vision and Pattern Recognition · Computer Science 2026-01-26 Xiang Fan , Sharath Girish , Vivek Ramanujan , Chaoyang Wang , Ashkan Mirzaei , Petr Sushko , Aliaksandr Siarohin , Sergey Tulyakov , Ranjay Krishna

While humans perceive the world through diverse modalities that operate synergistically to support a holistic understanding of their surroundings, existing omnivideo models still face substantial challenges on audio-visual understanding…

Artificial Intelligence · Computer Science 2026-02-17 Zhangquan Chen , Jiale Tao , Ruihuang Li , Yihao Hu , Ruitao Chen , Zhantao Yang , Xinlei Yu , Haodong Jing , Manyuan Zhang , Shuai Shao , Biao Wang , Qinglin Lu , Ruqi Huang

We propose a self-supervised shared encoder model that achieves strong results on several visual, language and multimodal benchmarks while being data, memory and run-time efficient. We make three key contributions. First, in contrast to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Rakesh Chada , Zhaoheng Zheng , Pradeep Natarajan

Humans can flexibly interpret and compose different goal specifications, such as language instructions, spatial coordinates, or visual references, when navigating to a destination. In contrast, most existing robotic navigation policies are…

Robotics · Computer Science 2025-09-25 Noriaki Hirose , Catherine Glossop , Dhruv Shah , Sergey Levine

The practical deployment of medical vision-language models (Med-VLMs) necessitates seamless integration of textual data with diverse visual modalities, including 2D/3D images and videos, yet existing models typically employ separate…

Computation and Language · Computer Science 2025-04-22 Songtao Jiang , Yuan Wang , Sibo Song , Yan Zhang , Zijie Meng , Bohan Lei , Jian Wu , Jimeng Sun , Zuozhu Liu

Videos are a rich source of multi-modal supervision. In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. To this end, we introduce the…

Computer Vision and Pattern Recognition · Computer Science 2020-11-02 Jean-Baptiste Alayrac , Adrià Recasens , Rosalia Schneider , Relja Arandjelović , Jason Ramapuram , Jeffrey De Fauw , Lucas Smaira , Sander Dieleman , Andrew Zisserman

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been…

Computer Vision and Pattern Recognition · Computer Science 2022-02-09 Kunchang Li , Yali Wang , Peng Gao , Guanglu Song , Yu Liu , Hongsheng Li , Yu Qiao

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 David Mizrahi , Roman Bachmann , Oğuzhan Fatih Kar , Teresa Yeo , Mingfei Gao , Afshin Dehghan , Amir Zamir

Recognizing human activities in videos is challenging due to the spatio-temporal complexity and context-dependence of human interactions. Prior studies often rely on single input modalities, such as RGB or skeletal data, limiting their…

Computer Vision and Pattern Recognition · Computer Science 2024-09-05 Tuyen Tran , Thao Minh Le , Hung Tran , Truyen Tran

Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Bonan Ding , Umair Nawaz , Ufaq Khan , Abdelrahman M. Shaker , Muhammad Haris Khan , Jiale Cao , Jin Xie , Fahad Shahbaz Khan

Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Yuanhuiyi Lyu , Xu Zheng , Dahun Kim , Lin Wang

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing narrowly in image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yibin Yan , Jilan Xu , Shangzhe Di , Haoning Wu , Weidi Xie

Unified video modeling that combines generation and understanding capabilities is increasingly important but faces two key challenges: maintaining semantic faithfulness during flow-based generation due to text-visual token imbalance and the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Jiabin Luo , Junhui Lin , Zeyu Zhang , Biao Wu , Meng Fang , Ling Chen , Hao Tang

Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We present CrossOver, a novel framework for cross-modal 3D scene…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Sayan Deb Sarkar , Ondrej Miksik , Marc Pollefeys , Daniel Barath , Iro Armeni

The objective of this paper is 3D shape understanding from single and multiple images. To this end, we introduce a new deep-learning architecture and loss function, SilNet, that can handle multiple views in an order-agnostic manner. The…

Computer Vision and Pattern Recognition · Computer Science 2017-11-22 Olivia Wiles , Andrew Zisserman

Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse inputs and perform diverse tasks are limited by the (usually rather small)…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Roman Bachmann , Oğuzhan Fatih Kar , David Mizrahi , Ali Garjani , Mingfei Gao , David Griffiths , Jiaming Hu , Afshin Dehghan , Amir Zamir

Recognizing scenes and objects in 3D from a single image is a longstanding goal of computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets and scalable solutions have led to unprecedented advances. In 3D,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Garrick Brazil , Abhinav Kumar , Julian Straub , Nikhila Ravi , Justin Johnson , Georgia Gkioxari

Multimodal multitask learning has attracted an increasing interest in recent years. Singlemodal models have been advancing rapidly and have achieved astonishing results on various tasks across multiple domains. Multimodal learning offers…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Ye Xue , Diego Klabjan , Jean Utke

Traditional systems typically require different models for processing different modalities, such as one model for RGB images and another for depth images. Recent research has demonstrated that a single model for one modality can be adapted…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Xiaoke Shen , Ioannis Stamos