中文
相关论文

相关论文: ERMV: Editing 4D Robotic Multi-view images to enha…

200 篇论文

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…

计算与语言 · 计算机科学 2024-10-16 Jingyuan Qi , Zhiyang Xu , Rulin Shao , Yang Chen , Jin Di , Yu Cheng , Qifan Wang , Lifu Huang

In Multimodal Language Models (MLMs), the cost of manually annotating high-quality image-text pair data for fine-tuning and alignment is extremely high. While existing multimodal data augmentation frameworks propose ways to augment…

人工智能 · 计算机科学 2024-08-20 Xiaomeng Jin , Jeonghwan Kim , Yu Zhou , Kuan-Hao Huang , Te-Lin Wu , Nanyun Peng , Heng Ji

Robotic manipulation, a key frontier in robotics and embodied AI, requires precise motor control and multimodal understanding, yet traditional rule-based methods fail to scale or generalize in unstructured, novel environments. In recent…

机器人学 · 计算机科学 2025-09-04 Rui Shao , Wei Li , Lingsen Zhang , Renshan Zhang , Zhiyang Liu , Ran Chen , Liqiang Nie

Joint Embedding Architecture-based self-supervised learning methods have attributed the composition of data augmentations as a crucial factor for their strong representation learning capabilities. While regional dropout strategies have…

计算机视觉与模式识别 · 计算机科学 2023-09-08 Arjon Das , Xin Zhong

Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, enabling agents to leverage commonsense and spatial reasoning for efficient exploration in…

Vision-Language-Action (VLA) models have emerged as a promising approach for enabling robots to follow language instructions and predict corresponding actions. However, current VLA models mainly rely on 2D visual inputs, neglecting the rich…

机器人学 · 计算机科学 2025-08-14 Lin Sun , Bin Xie , Yingfei Liu , Hao Shi , Tiancai Wang , Jiale Cao

As embodied agents operate in increasingly complex environments, the ability to perceive, track, and reason about individual object instances over time becomes essential, especially in tasks requiring sequenced interactions with visually…

The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data…

计算机视觉与模式识别 · 计算机科学 2021-10-18 Dhruv Sharma , Alihusein Kuwajerwala , Florian Shkurti

Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene…

机器人学 · 计算机科学 2024-12-18 Qi Sun , Pengfei Hong , Tej Deep Pala , Vernon Toh , U-Xuan Tan , Deepanway Ghosal , Soujanya Poria

Pre-trained Vision-Language Models (VLMs) have been exploited in various Computer Vision tasks (e.g., few-shot recognition) via model adaptation, such as prompt tuning and adapters. However, existing adaptation methods are designed by human…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Kun Ding , Ying Wang , Shiming Xiang

Medical Vision-Language Models (VLMs) hold immense promise for complex clinical tasks, but their reasoning capabilities are often constrained by text-only paradigms that fail to ground inferences in visual evidence. This limitation not only…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Zheng Jiang , Heng Guo , Chengyu Fang , Changchen Xiao , Xinyang Hu , Lifeng Sun , Minfeng Xu

Recent progress in robot learning has been driven by large-scale datasets and powerful visuomotor policy architectures, yet policy robustness remains limited by the substantial cost of collecting diverse demonstrations, particularly for…

机器人学 · 计算机科学 2026-03-24 Yujie Zhao , Hongwei Fan , Di Chen , Shengcong Chen , Liliang Chen , Xiaoqi Li , Guanghui Ren , Hao Dong

Visual Robot Manipulation (VRM) aims to enable a robot to follow natural language instructions based on robot states and visual observations, and therefore requires costly multi-modal data. To compensate for the deficiency of robot data,…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Dejie Yang , Zijing Zhao , Yang Liu

Existing video self-supervised learning methods mainly rely on trimmed videos for model training. However, trimmed datasets are manually annotated from untrimmed videos. In this sense, these methods are not really self-supervised. In this…

计算机视觉与模式识别 · 计算机科学 2020-08-07 Dezhao Luo , Bo Fang , Yu Zhou , Yucan Zhou , Dayan Wu , Weiping Wang

The advancement of embodied intelligence is accelerating the integration of robots into daily life as human assistants. This evolution requires robots to not only interpret high-level instructions and plan tasks but also perceive and adapt…

机器人学 · 计算机科学 2025-08-19 Zhichen Lou , Kechun Xu , Zhongxiang Zhou , Rong Xiong

Multi-view 3D object detection is a fundamental task in autonomous driving perception, where achieving a balance between detection accuracy and computational efficiency remains crucial. Sparse query-based 3D detectors efficiently aggregate…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Di Wu , Feng Yang , Wenhui Zhao , Jinwen Yu , Pan Liao , Benlian Xu , Dingwen Zhang

Masked Video Autoencoder (MVA) approaches have demonstrated their potential by significantly outperforming previous video representation learning methods. However, they waste an excessive amount of computations and memory in predicting…

计算机视觉与模式识别 · 计算机科学 2024-06-21 Sunil Hwang , Jaehong Yoon , Youngwan Lee , Sung Ju Hwang

In this work, we present VARGPT-v1.1, an advanced unified visual autoregressive model that builds upon our previous framework VARGPT. The model preserves the dual paradigm of next-token prediction for visual understanding and next-scale…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Xianwei Zhuang , Yuxin Xie , Yufan Deng , Dongchao Yang , Liming Liang , Jinghan Ru , Yuguo Yin , Yuexian Zou

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

人工智能 · 计算机科学 2025-04-18 Baining Zhao , Ziyou Wang , Jianjie Fang , Chen Gao , Fanhang Man , Jinqiang Cui , Xin Wang , Xinlei Chen , Yong Li , Wenwu Zhu

Recent Multimodal Large Language Models (MLLMs) have shown high potential for spatial reasoning within 3D scenes. However, they typically rely on computationally expensive 3D representations like point clouds or reconstructed Bird's-Eye…

计算机视觉与模式识别 · 计算机科学 2026-05-08 Shuyao Shi , Kang G. Shin