English
Related papers

Related papers: A Light-Weight Contrastive Approach for Aligning H…

200 papers

Although monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view information is a practical way to achieve absolute 3D human…

Computer Vision and Pattern Recognition · Computer Science 2022-05-18 Guoliang Hua , Hong Liu , Wenhao Li , Qian Zhang , Runwei Ding , Xin Xu

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Vlad Sobal , Mark Ibrahim , Randall Balestriero , Vivien Cabannes , Diane Bouchacourt , Pietro Astolfi , Kyunghyun Cho , Yann LeCun

A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting with contrastive…

Computation and Language · Computer Science 2025-10-17 Jingcheng Deng , Zhongtao Jiang , Liang Pang , Liwei Chen , Kun Xu , Zihao Wei , Huawei Shen , Xueqi Cheng

This paper presents miCSE, a mutual information-based contrastive learning framework that significantly advances the state-of-the-art in few-shot sentence embedding. The proposed approach imposes alignment between the attention pattern of…

Computation and Language · Computer Science 2023-05-24 Tassilo Klein , Moin Nabi

We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fuse input images into…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Edoardo Remelli , Shangchen Han , Sina Honari , Pascal Fua , Robert Wang

Supervised learning of skeleton sequence encoders for action recognition has received significant attention in recent times. However, learning such encoders without labels continues to be a challenging problem. While prior works have shown…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Anshul Shah , Aniket Roy , Ketul Shah , Shlok Kumar Mishra , David Jacobs , Anoop Cherian , Rama Chellappa

We propose a simple and efficient method for exploiting synthetic images when training a Deep Network to predict a 3D pose from an image. The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Mahdi Rad , Markus Oberweger , Vincent Lepetit

Numerous methods have been proposed to adapt a pre-trained foundational CLIP model for few-shot classification. As CLIP is trained on a large corpus, it generalises well through adaptation to few-shot classification. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Alexey Kravets , Vinay Namboodiri

Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based methods generally recover human mesh by estimating the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Yingxuan You , Hong Liu , Ti Wang , Wenhao Li , Runwei Ding , Xia Li

With an aim to increase the capture range and accelerate the performance of state-of-the-art inter-subject and subject-to-template 3D registration, we propose deep learning-based methods that are trained to find the 3D position of…

Computer Vision and Pattern Recognition · Computer Science 2018-08-21 Seyed Sadegh Mohseni Salehi , Shadab Khan , Deniz Erdogmus , Ali Gholipour

The goal of many computer vision systems is to transform image pixels into 3D representations. Recent popular models use neural networks to regress directly from pixels to 3D object parameters. Such an approach works well when supervision…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Nadine Rueegg , Christoph Lassner , Michael J. Black , Konrad Schindler

This paper addresses the challenge of 3D full-body human pose estimation from a monocular image sequence. Here, two cases are considered: (i) the image locations of the human joints are provided and (ii) the image locations of joints are…

Computer Vision and Pattern Recognition · Computer Science 2016-04-29 Xiaowei Zhou , Menglong Zhu , Spyridon Leonardos , Kosta Derpanis , Kostas Daniilidis

Available 3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision. Barring synthetic or in-studio domains, acquiring such supervision for each new target…

Computer Vision and Pattern Recognition · Computer Science 2022-04-07 Jogendra Nath Kundu , Siddharth Seth , Anirudh Jamkhandi , Pradyumna YM , Varun Jampani , Anirban Chakraborty , R. Venkatesh Babu

In natural language processing (NLP) of spoken languages, word embeddings have been shown to be a useful method to encode the meaning of words. Sign languages are visual languages, which require sign embeddings to capture the visual and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Ryan Wong , Necati Cihan Camgoz , Richard Bowden

Recent advancements in visual localization and mapping have demonstrated considerable success in integrating point and line features. However, expanding the localization framework to include additional mapping components frequently results…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Bach-Thuan Bui , Huy-Hoang Bui , Dinh-Tuan Tran , Joo-Ho Lee

A key challenge in contrastive learning is to generate negative samples from a large sample set to contrast with positive samples, for learning better encoding of the data. These negative samples often follow a softmax distribution which…

Machine Learning · Computer Science 2024-04-17 Chung-Yiu Yau , Hoi-To Wai , Parameswaran Raman , Soumajyoti Sarkar , Mingyi Hong

We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Jian Liu , Naveed Akhtar , Ajmal Mian

We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network. In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part…

Computer Vision and Pattern Recognition · Computer Science 2014-06-16 Sijin Li , Zhi-Qiang Liu , Antoni B. Chan

Few-Shot learning aims to train and optimize a model that can adapt to unseen visual classes with only a few labeled examples. The existing few-shot learning (FSL) methods, heavily rely only on visual data, thus fail to capture the semantic…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Mohamed Afham , Ranga Rodrigo

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map…

Machine Learning · Computer Science 2021-10-27 Alexander Scheinker