中文
相关论文

相关论文: Contrastively Learning Visual Attention as Afforda…

200 篇论文

Motivated by the intuitive understanding humans have about the space of possible interactions, and the ease with which they can generalize this understanding to previously unseen scenes, we develop an approach for learning visual…

机器人学 · 计算机科学 2023-05-30 Homanga Bharadhwaj , Abhinav Gupta , Shubham Tulsiani

A core problem of Embodied AI is to learn object manipulation from observation, as humans do. To achieve this, it is important to localize 3D object affordance areas through observation such as images (3D affordance grounding) and…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Xinhang Wan , Dongqiang Gou , Xinwang Liu , En Zhu , Xuming He

Affordance is crucial for intelligent robots in the context of object manipulation. In this paper, we argue that affordance should be task-/instruction-dependent, which is overlooked by many previous works. That is, different instructions…

机器人学 · 计算机科学 2025-08-26 Bokai Ji , Jie Gu , Xiaokang Ma , Chu Tang , Jingmin Chen , Guangxia Li

The term "affordance" denotes the behavioral meaning of objects. We propose a cognitive architecture for the detection of affordances in the visual modality. This model is based on the internal simulation of movement sequences. For each…

人工智能 · 计算机科学 2016-11-02 Wolfram Schenck , Hendrik Hasenbein , Ralf Möller

In this paper, we investigate the effectiveness of contrastive learning methods for predicting grasp outcomes in an unsupervised manner. By utilizing a publicly available dataset, we demonstrate that contrastive learning methods perform…

机器人学 · 计算机科学 2023-09-22 Chengliang Liu , Binhua Huang , Yiwen Liu , Yuanzhe Su , Ke Mai , Yupo Zhang , Zhengkun Yi , Xinyu Wu

With the escalated demand of human-machine interfaces for intelligent systems, development of gaze controlled system have become a necessity. Gaze, being the non-intrusive form of human interaction, is one of the best suited approach.…

计算机视觉与模式识别 · 计算机科学 2023-08-08 Somsukla Maiti , Akshansh Gupta

We present a framework for assistive robot manipulation, which focuses on two fundamental challenges: first, efficiently adapting large-scale models to downstream scene affordance understanding tasks, especially in daily living scenarios…

机器人学 · 计算机科学 2025-11-10 Fan Zhang , Michael Gienger

Lexical semantics and cognitive science point to affordances (i.e. the actions that objects support) as critical for understanding and representing nouns and verbs. However, study of these semantic features has not yet been integrated with…

计算与语言 · 计算机科学 2022-07-07 Jack Merullo , Dylan Ebert , Carsten Eickhoff , Ellie Pavlick

Understanding and manipulating deformable objects (e.g., ropes and fabrics) is an essential yet challenging task with broad applications. Difficulties come from complex states and dynamics, diverse configurations and high-dimensional action…

计算机视觉与模式识别 · 计算机科学 2023-07-24 Ruihai Wu , Chuanruo Ning , Hao Dong

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong…

计算机视觉与模式识别 · 计算机科学 2023-04-05 Ruchika Chavhan , Henry Gouk , Jan Stuehmer , Calum Heggan , Mehrdad Yaghoobi , Timothy Hospedales

Road attributes understanding is extensively researched to support vehicle's action for autonomous driving, whereas current works mainly focus on urban road nets and rely much on traffic signs. This paper generalizes the same issue to the…

机器人学 · 计算机科学 2019-11-28 Huifang Ma , Yue Wang , Rong Xiong , Sarath Kodagoda , Qianhui Luo

Achieving precise and generalizable grasping across diverse objects and environments is essential for intelligent and collaborative robotic systems. However, existing approaches often struggle with ambiguous affordance reasoning and limited…

机器人学 · 计算机科学 2025-03-11 Ruixiang Wang , Huayi Zhou , Xinyue Yao , Guiliang Liu , Kui Jia

Today, there are two major paradigms for vision-based autonomous driving systems: mediated perception approaches that parse an entire scene to make a driving decision, and behavior reflex approaches that directly map an input image to a…

计算机视觉与模式识别 · 计算机科学 2015-09-29 Chenyi Chen , Ari Seff , Alain Kornhauser , Jianxiong Xiao

This paper presents a framework for learning visual representations from unlabeled video demonstrations captured from multiple viewpoints. We show that these representations are applicable for imitating several robotic tasks, including pick…

计算机视觉与模式识别 · 计算机科学 2023-01-30 André Correia , Luís A. Alexandre

Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in…

机器学习 · 计算机科学 2022-05-03 Ralph Peeters , Christian Bizer

Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can…

计算与语言 · 计算机科学 2021-10-22 Peng Xu , Xinchi Chen , Xiaofei Ma , Zhiheng Huang , Bing Xiang

When humans perform a task with an articulated object, they interact with the object only in a handful of ways, while the space of all possible interactions is nearly endless. This is because humans have prior knowledge about what…

计算机视觉与模式识别 · 计算机科学 2023-05-30 Liquan Wang , Nikita Dvornik , Rafael Dubeau , Mayank Mittal , Animesh Garg

We explore how intermediate policy representations can facilitate generalization by providing guidance on how to perform manipulation tasks. Existing representations such as language, goal images, and trajectory sketches have been shown to…

机器人学 · 计算机科学 2024-11-06 Soroush Nasiriany , Sean Kirmani , Tianli Ding , Laura Smith , Yuke Zhu , Danny Driess , Dorsa Sadigh , Ted Xiao

Affordance information about a scene provides important clues as to what actions may be executed in pursuit of meeting a specified goal state. Thus, integrating affordance-based reasoning into symbolic action plannning pipelines would…

机器人学 · 计算机科学 2020-09-15 Fu-Jen Chu , Ruinian Xu , Chao Tang , Patricio A. Vela

The ability to understand the ways to interact with objects from visual cues, a.k.a. visual affordance, is essential to vision-guided robotic research. This involves categorizing, segmenting and reasoning of visual affordance. Relevant…

计算机视觉与模式识别 · 计算机科学 2021-04-01 Shengheng Deng , Xun Xu , Chaozheng Wu , Ke Chen , Kui Jia