English
Related papers

Related papers: Representation Alignment Contrastive Regularizatio…

200 papers

Effective task representations should facilitate compositionality, such that after learning a variety of basic tasks, an agent can perform compound tasks consisting of multiple steps simply by composing the representations of the…

Robotics · Computer Science 2025-02-14 Vivek Myers , Bill Chunyuan Zheng , Anca Dragan , Kuan Fang , Sergey Levine

High-dimensional multivariate spatial-temporal data arise frequently in a wide range of applications; however, there are relatively few statistical methods that can simultaneously deal with spatial, temporal and variable-wise dependencies…

Methodology · Statistics 2020-02-05 Elynn Y. Chen , Xin Yun , Rong Chen , Qiwei Yao

Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Giordano Cicchetti , Eleonora Grassucci , Luigi Sigillo , Danilo Comminiello

Visual Object tracking research has undergone significant improvement in the past few years. The emergence of tracking by detection approach in tracking paradigm has been quite successful in many ways. Recently, deep convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2017-11-23 Litu Rout , Sidhartha , Gorthi R. K. S. S. Manyam , Deepak Mishra

Recently, dense contrastive learning has shown superior performance on dense prediction tasks compared to instance-level contrastive learning. Despite its supremacy, the properties of dense contrastive representations have not yet been…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Jong Hak Moon , Wonjae Kim , Edward Choi

Cooperative perception presents significant potential for enhancing the sensing capabilities of individual vehicles, however, inter-agent latency remains a critical challenge. Latencies cause misalignments in both spatial and semantic…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Zhiying Song , Lei Yang , Fuxi Wen , Jun Li

This paper introduces a novel framework to learn data association for multi-object tracking in a self-supervised manner. Fully-supervised learning methods are known to achieve excellent tracking performances, but acquiring identity-level…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Shuai Li , Michael Burke , Subramanian Ramamoorthy , Juergen Gall

Spatio-temporal traffic forecasting is challenging due to complex temporal patterns, dynamic spatial structures, and diverse input formats. Although Transformer-based models offer strong global modeling, they often struggle with rigid…

Artificial Intelligence · Computer Science 2025-08-20 Jiayu Fang , Zhiqi Shao , S T Boris Choy , Junbin Gao

Registration of multivariate functional data involves handling of both cross-component and cross-observation phase variations. Allowing for the two phase variations to be modelled as general diffeomorphic time warpings, in this work we…

Methodology · Statistics 2022-07-25 Xiaohan Guo , Sebastian Kurtek , Karthik Bharath

Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Yu Wang , Sanping Zhou , Kun Xia , Le Wang

Most object manipulation strategies for robots are based on the assumption that the object is rigid (i.e., with fixed geometry) and the goal's details have been fully specified (e.g., the exact target pose). However, there are many tasks…

Robotics · Computer Science 2022-09-14 Shengzeng Huo , Fangyuan Wang , Luyin Hu , Peng Zhou , Jihong Zhu , Hesheng Wang , David Navarro-Alarcon

While large volumes of unlabeled data are usually available, associated labels are often scarce. The unsupervised domain adaptation problem aims at exploiting labels from a source domain to classify data from a related, yet different,…

Machine Learning · Computer Science 2023-08-28 François Painblanc , Laetitia Chapel , Nicolas Courty , Chloé Friguet , Charlotte Pelletier , Romain Tavenard

This paper addresses the problem of appearance matching across different challenges while doing visual face tracking in real-world scenarios. In this paper, FaceTrack is proposed that utilizes multiple appearance models with its long-term…

Computer Vision and Pattern Recognition · Computer Science 2018-08-31 Tanushri Chakravorty , Guillaume-Alexandre Bilodeau , Eric Granger

Accurately predicting the likelihood of interaction between two objects (compound-protein sequence, user-item, author-paper, etc.) is a fundamental problem in Computer Science. Current deep-learning models rely on learning accurate…

Machine Learning · Computer Science 2022-12-23 Apurva Kalia , Dilip Krishnan , Soha Hassoun

Directly learning multiple 3D objects motion from sequential images is difficult, while the geometric bundle adjustment lacks the ability to localize the invisible object centroid. To benefit from both the powerful object understanding…

Computer Vision and Pattern Recognition · Computer Science 2020-04-21 Peiliang Li , Jieqi Shi , Shaojie Shen

Deformable parts models show a great potential in tracking by principally addressing non-rigid object deformations and self occlusions, but according to recent benchmarks, they often lag behind the holistic approaches. The reason is that…

Computer Vision and Pattern Recognition · Computer Science 2016-05-13 Alan Lukežič , Luka Čehovin , Matej Kristan

Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…

Machine Learning · Statistics 2025-06-02 Ricardo Baptista , Andrew M. Stuart , Son Tran

This paper presents a novel approach for representing proprioceptive time-series data from quadruped robots as structured two-dimensional images, enabling the use of convolutional neural networks for learning locomotion-related tasks. The…

Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Zhirui Gao , Renjiao Yi , Zheng Qin , Yunfan Ye , Chenyang Zhu , Kai Xu

The goal of multi-object tracking (MOT) is to detect and track all objects in a scene across frames, while maintaining a unique identity for each object. Most existing methods rely on the spatial-temporal motion features and appearance…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Yanzhao Fang