English
Related papers

Related papers: Learning the RoPEs: Better 2D and 3D Position Enco…

200 papers

In many computer vision applications, images are acquired with arbitrary or random rotations and translations, and in such setups, it is desirable to obtain semantic representations disentangled from the image orientation. Examples of such…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Sehyun Kwon , Joo Young Choi , Ernest K. Ryu

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Dong Lao , Yangchao Wu , Tian Yu Liu , Alex Wong , Stefano Soatto

Neural encoder-decoder models have been successful in natural language generation tasks. However, real applications of abstractive summarization must consider additional constraint that a generated summary should not exceed a desired…

Computation and Language · Computer Science 2019-04-17 Sho Takase , Naoaki Okazaki

Position encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. However, in…

Computation and Language · Computer Science 2020-11-24 Liang Ding , Longyue Wang , Dacheng Tao

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…

Cross-view object geo-localization enables high-precision object localization through cross-view matching, with critical applications in autonomous driving, urban management, and disaster response. However, existing methods rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Shuhan Hu , Yiru Li , Yuanyuan Li , Yingying Zhu

In recent years, vision transformers with text decoder have demonstrated remarkable performance on Scene Text Recognition (STR) due to their ability to capture long-range dependencies and contextual relationships with high learning…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Savas Ozkan , Andrea Maracani , Hyowon Kim , Sijun Cho , Eunchung Noh , Jeongwon Min , Jung Min Cho , Mete Ozay

An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded…

Machine Learning · Computer Science 2025-11-18 Felipe Urrutia , Jorge Salas , Alexander Kozachinskiy , Cristian Buc Calderon , Hector Pasten , Cristobal Rojas

Predictive process monitoring is a process mining task aimed at forecasting information about a running process trace, such as the most correct next activity to be executed. In medical domains, predictive process monitoring can provide…

Machine Learning · Computer Science 2026-02-18 Christopher Irwin , Marco Dossena , Giorgio Leonardi , Stefania Montani

Positional encodings enable Transformers to incorporate sequential information, yet their theoretical understanding remains limited to two properties: distance attenuation and translation invariance. Because natural language lacks purely…

Machine Learning · Computer Science 2026-02-11 Zihan Gu , Ruoyu Chen , Han Zhang , Hua Zhang , Yue Hu

We present a framework to translate between 2D image views and 3D object shapes. Recent progress in deep learning enabled us to learn structure-aware representations from a scene. However, the existing literature assumes that pairs of…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Berk Kaya , Radu Timofte

In this work we present a novel end-to-end framework for tracking and classifying a robot's surroundings in complex, dynamic and only partially observable real-world environments. The approach deploys a recurrent neural network to filter an…

Machine Learning · Computer Science 2016-04-20 Peter Ondruska , Julie Dequaire , Dominic Zeng Wang , Ingmar Posner

Autonomous robots require change-robust spatial-semantic reasoning: using spatial and semantic knowledge to decide where to go, how to get there, and where the robot is despite environmental change. Existing approaches typically attach…

Robotics · Computer Science 2026-05-05 Jiaming Wang , Jizhuo Chen , Diwen Liu , Atharva Ghotavadekar , Jiaxuan Da , Linh Kästner , Harold Soh

We conducted empirical experiments to assess the transferability of a light curve transformer to datasets with different cadences and magnitude distributions using various positional encodings (PEs). We proposed a new approach to…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

This manuscript investigates the integration of positional encoding -- a technique widely used in computer graphics -- into the input vector of a binary classification model for self-collision detection. The results demonstrate the benefits…

Robotics · Computer Science 2026-04-21 Bartłomiej Kulecki , Dominik Belter

Context-aware translation can be achieved by processing a concatenation of consecutive sentences with the standard Transformer architecture. This paper investigates the intuitive idea of providing the model with explicit information about…

Computation and Language · Computer Science 2023-04-06 Lorenzo Lupo , Marco Dinarelli , Laurent Besacier

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or…

Computation and Language · Computer Science 2019-06-05 Fengshun Xiao , Jiangtong Li , Hai Zhao , Rui Wang , Kehai Chen

In this paper, it is proved that dictionary learning and sparse representation is invariant to a linear transformation. It subsumes the special case of transforming/projecting the data into a discriminative space. This is important because…

Computer Vision and Pattern Recognition · Computer Science 2015-06-12 Mehrdad J. Gangeh , Ali Ghodsi

Robots that can manipulate objects in unstructured environments and collaborate with humans can benefit immensely by understanding natural language. We propose a pipelined architecture of two stages to perform spatial reasoning on the text…