相关论文: Closed-Loop Transfer for Weakly-supervised Afforda…

Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt…

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

We present a new implicit warping framework for image animation using sets of source images through the transfer of the motion of a driving video. A single cross- modal attention layer is used to find correspondences between the source…

Intelligent manipulation benefits from the capacity to flexibly control an end-effector with high degrees of freedom (DoF) and dynamically react to the environment. However, due to the challenges of collecting effective training data and…

Egocentric video recognition is a natural testbed for diverse interaction reasoning. Due to the large action vocabulary in egocentric video datasets, recent studies usually utilize a two-branch structure for action recognition, ie, one…

Transfer learning is a powerful way to adapt existing deep learning models to new emerging use-cases in remote sensing. Starting from a neural network already trained for semantic segmentation, we propose to modify its label space to…

A large gap exists between fully-supervised object detection and weakly-supervised object detection. To narrow this gap, some methods consider knowledge transfer from additional fully-supervised dataset. But these methods do not fully…

Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions. Two fundamental limitations of these methods are that most require a full model of the environment…

Humans have a unique ability to learn new representations from just a handful of examples with little to no supervision. Deep learning models, however, require an abundance of data and supervision to perform at a satisfactory level.…

Learning robot manipulation from human videos is appealing due to the scale and diversity of human demonstrations, but transferring such demonstrations to executable robot behavior remains challenging. Prior work either relies on robot data…

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as…

Recognizing fine-grained categories remains a challenging task, due to the subtle distinctions among different subordinate categories, which results in the need of abundant annotated samples. To alleviate the data-hungry problem, we…

Dexterous grasp synthesis must jointly satisfy functional intent and physical feasibility, yet existing pipelines often decouple semantic grounding from refinement, yielding unstable or non-functional contacts under object and pose…

Global perception is essential for embodied agents in 360{\deg} spaces, yet current affordance grounding remains largely object-centric and restricted to perspective views. To bridge this gap, we introduce a novel task: Holistic Affordance…

Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural networks outperform traditional approaches based on extraction…

We investigate the knowledge of object affordances in pre-trained language models (LMs) and pre-trained Vision-Language models (VLMs). A growing body of literature shows that PTLMs fail inconsistently and non-intuitively, demonstrating a…

Mining precise class-aware attention maps, a.k.a, class activation maps, is essential for weakly supervised semantic segmentation. In this paper, we present L2G, a simple online local-to-global knowledge transfer framework for high-quality…

In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as…

Weakly supervised object localization (WSOL) aims to learn object localizer solely by using image-level labels. The convolution neural network (CNN) based techniques often result in highlighting the most discriminative part of objects while…

In this abstract we describe recent [4,7] and latest work on the determination of affordances in visually perceived 3D scenes. Our method builds on the hypothesis that geometry on its own provides enough information to enable the detection…