English
Related papers

Related papers: Tiled Squeeze-and-Excite: Channel Attention With L…

200 papers

Unsupervised segmentation approaches have increasingly leveraged foundation models (FM) to improve salient object discovery. However, these methods often falter in scenes with complex, multi-component morphologies, where fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Deepank Singh , Anurag Nihal , Vedhus Hoskere

Temporal modeling is key for action recognition in videos. It normally considers both short-range motions and long-range aggregations. In this paper, we propose a Temporal Excitation and Aggregation (TEA) block, including a motion…

Computer Vision and Pattern Recognition · Computer Science 2020-04-06 Yan Li , Bin Ji , Xintian Shi , Jianguo Zhang , Bin Kang , Limin Wang

Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities…

Computer Vision and Pattern Recognition · Computer Science 2017-04-13 Long Chen , Hanwang Zhang , Jun Xiao , Liqiang Nie , Jian Shao , Wei Liu , Tat-Seng Chua

Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to…

Computation and Language · Computer Science 2024-05-29 Jie Wang , Tao Ji , Yuanbin Wu , Hang Yan , Tao Gui , Qi Zhang , Xuanjing Huang , Xiaoling Wang

Efficiently processing long sequences with Transformer models usually requires splitting the computations across accelerators via context parallelism. The dominant approaches in this family of methods, such as Ring Attention or DeepSpeed…

Machine Learning · Computer Science 2026-02-25 Ravi Ghadia , Maksim Abraham , Sergei Vorobyov , Max Ryabinin

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…

Computation and Language · Computer Science 2026-02-03 J Rosser , José Luis Redondo García , Gustavo Penha , Konstantina Palla , Hugues Bouchard

Performance of sound event localization and detection (SELD) in real scenes is limited by small size of SELD dataset, due to difficulty in obtaining sufficient amount of realistic multi-channel audio data recordings with accurate label. We…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-27 Byeong-Yun Ko , Hyeonuk Nam , Seong-Hu Kim , Deokki Min , Seung-Deok Choi , Yong-Hwa Park

Recent advancements in discrete image generation showed that scaling the VQ codebook size significantly improves reconstruction fidelity. However, training generative models with a large VQ codebook remains challenging, typically requiring…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Shufan Li , Jiuxiang Gu , Kangning Liu , Zhe Lin , Aditya Grover , Jason Kuen

In robotics, diffusion models can capture multi-modal trajectories from demonstrations, making them a transformative approach in imitation learning. However, achieving optimal performance following this regiment requires a large-scale…

Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that this problem mainly stems from the asymmetric properties…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Hang Yin , Xiaomin He , PeiWen Yuan , Yiwei Li , Jiayi Shi , Wenxiao Fan , Shaoxiong Feng , Kan Li

Target Speaker Extraction (TSE) aims to isolate a specific speaker's voice from a mixture, guided by a pre-recorded enrollment. While TSE bypasses the global permutation ambiguity of blind source separation, it remains vulnerable to speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-10 Zikai Liu , Ziqian Wang , Xingchen Li , Yike Zhu , Shuai Wang , Longshuai Xiao , Lei Xie

Recently many effective attention modules are proposed to boot the model performance by exploiting the internal information of convolutional neural networks in computer vision. In general, many previous works ignore considering the design…

Machine Learning · Computer Science 2022-10-25 Shanshan Zhong , Wushao Wen , Jinghui Qin

Active event perception, the ability to dynamically detect, track, and summarize events in real time, is essential for embodied intelligence in tasks such as human-AI collaboration, assistive robotics, and autonomous navigation. However,…

Robotics · Computer Science 2025-06-24 Zhou Chen , Sanjoy Kundu , Harsimran S. Baweja , Sathyanarayanan N. Aakur

High-quality saliency maps are essential in several machine learning application areas including explainable AI and weakly supervised object detection and segmentation. Many techniques have been developed to generate better saliency using…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Osman Tursun , Simon Denman , Sridha Sridharan , Clinton Fookes

Spatiotemporal predictive learning (ST-PL) is a hotspot with numerous applications, such as object movement and meteorological prediction. It aims at predicting the subsequent frames via observed sequences. However, inherent uncertainty…

Computer Vision and Pattern Recognition · Computer Science 2022-04-13 Zenghao Chai , Zhengzhuo Xu , Yunpeng Bai , Zhihui Lin , Chun Yuan

Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Shunpeng Chen , Changwei Wang , Rongtao Xu , Xingtian Pei , Yukun Song , Jinzhou Lin , Wenhao Xu , Jingyi Zhang , Li Guo , Shibiao Xu

In this work, we propose a generally applicable transformation unit for visual recognition with deep convolutional neural networks. This transformation explicitly models channel relationships with explainable control variables. These…

Computer Vision and Pattern Recognition · Computer Science 2020-03-30 Zongxin Yang , Linchao Zhu , Yu Wu , Yi Yang

Multiple wireless sensing tasks, e.g., radar detection for driver safety, involve estimating the "channel" or relationship between signal transmitted and received. In this work, we focus on a certain channel model known as the delay-doppler…

Information Theory · Computer Science 2020-11-24 Alisha Zachariah

The object sizes in images are diverse, therefore, capturing multiple scale context information is essential for semantic segmentation. Existing context aggregation methods such as pyramid pooling module (PPM) and atrous spatial pyramid…

Computer Vision and Pattern Recognition · Computer Science 2019-07-16 Congcong Wang , Faouzi Alaya Cheikh , Azeddine Beghdadi , Ole Jakob Elle

Target speaker extraction (TSE) aims to recover a target speaker's speech from a mixture using a reference utterance as a cue. Most TSE systems adopt conditional auto-encoder architectures with one-step inference. Inspired by test-time…

Sound · Computer Science 2026-03-12 Zhenghai You , Ying Shi , Lantian Li , Dong Wang