English
Related papers

Related papers: DemaFormer: Damped Exponential Moving Average Tran…

200 papers

The decoder-only Transformer architecture with causal masking and relative position encoding (RPE) has become the de facto choice in language modeling. Despite its exceptional performance across various tasks, we have identified two…

Computation and Language · Computer Science 2024-02-08 Qingyu Yin , Xuzheng He , Xiang Zhuang , Yu Zhao , Jianhua Yao , Xiaoyu Shen , Qiang Zhang

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Juncheng Yang , Zuchao Li , Shuai Xie , Weiping Zhu , Wei Yu , Shijun Li

Referring image segmentation aims to segment the image region of interest according to the given language expression, which is a typical multi-modal task. Existing methods either adopt the pixel classification-based or the learnable…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Zhichao Wei , Xiaohao Chen , Mingqiang Chen , Siyu Zhu

Interpreting EEG signals linked to spoken language presents a complex challenge, given the data's intricate temporal and spatial attributes, as well as the various noise factors. Denoising diffusion probabilistic models (DDPMs), which have…

Computation and Language · Computer Science 2023-11-15 Soowon Kim , Seo-Hyun Lee , Young-Eun Lee , Ji-Won Lee , Ji-Ha Park , Seong-Whan Lee

Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex motions that natural…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Aritra Bhowmik , Denis Korzhenkov , Cees G. M. Snoek , Amirhossein Habibian , Mohsen Ghafoorian

We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) that outperforms conventional softmax attention-based models in terms of both accuracy and efficiency. TransNormerLLM evolves from the previous linear…

Computation and Language · Computer Science 2024-01-22 Zhen Qin , Dong Li , Weigao Sun , Weixuan Sun , Xuyang Shen , Xiaodong Han , Yunshen Wei , Baohong Lv , Xiao Luo , Yu Qiao , Yiran Zhong

Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose DAMM, Dual-stream Attention with Multi-Modal queries, a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Noreen Anwar , Guillaume-Alexandre Bilodeau , Wassim Bouachir

Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this…

Machine Learning · Computer Science 2024-06-04 Romain Ilbert , Ambroise Odonnat , Vasilii Feofanov , Aladin Virmaux , Giuseppe Paolo , Themis Palpanas , Ievgen Redko

Temporal Action Localization (TAL) remains a fundamental challenge in video understanding, aiming to identify the start time, end time, and category of all action instances within untrimmed videos. While recent single-stage, anchor-free…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Thisara Rathnayaka , Uthayasanker Thayasivam

In previous work, we have proposed the Audio-Visual Scene-Aware Dialog (AVSD) task, collected an AVSD dataset, developed AVSD technologies, and hosted an AVSD challenge track at both the 7th and 8th Dialog System Technology Challenges…

Computation and Language · Computer Science 2021-10-14 Ankit P. Shah , Shijie Geng , Peng Gao , Anoop Cherian , Takaaki Hori , Tim K. Marks , Jonathan Le Roux , Chiori Hori

This paper addresses the problem of modeling textual conversations and detecting emotions. Our proposed model makes use of 1) deep transfer learning rather than the classical shallow methods of word embedding; 2) self-attention mechanisms…

Computation and Language · Computer Science 2019-06-18 Waleed Ragheb , Jérôme Azé , Sandra Bringay , Maximilien Servajean

Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress video tokens to reduce temporal resolution, or treat videos as…

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Computation and Language · Computer Science 2023-10-20 Qingru Zhang , Dhananjay Ram , Cole Hawkins , Sheng Zha , Tuo Zhao

Temporal sentence grounding (TSG) is a highly challenging task aiming to localize the temporal segment within an untrimmed video corresponding to a given natural language description. Benefiting from the design of learnable queries, the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Yifan Wang , Ziyi Liu , Xiaolong Sun , Jiawei Wang , Hongmin Liu

Talking face generation is a novel and challenging generation task, aiming at synthesizing a vivid speaking-face video given a specific audio. To fulfill emotion-controllable talking face generation, current methods need to overcome two…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Ziqi Zhang , Cheng Deng

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

Image and Video Processing · Electrical Eng. & Systems 2024-02-28 A. Burakhan Koyuncu , Panqi Jia , Atanas Boev , Elena Alshina , Eckehard Steinbach

Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Although previous respectable works have made decent success, they only focus on high-level visual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Xiang Fang , Daizong Liu , Pan Zhou , Guoshun Nan

Video moment retrieval (VMR) identifies a specific moment in an untrimmed video for a given natural language query. This task is prone to suffer the weak alignment problem innate in video datasets. Due to the ambiguity, a query does not…

Computer Vision and Pattern Recognition · Computer Science 2024-10-02 Minjoon Jung , Youwon Jang , Seongho Choi , Joochan Kim , Jin-Hwa Kim , Byoung-Tak Zhang

Recent advances in diffusion-based text-to-video models, particularly those built on the diffusion transformer architecture, have achieved remarkable progress in generating high-quality and temporally coherent videos. However, transferring…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Zhexin Zhang , Yangyang Xu , Yifeng Zhu , Long Chen , Yong Du , Shengfeng He , Jun Yu

In vision-based action recognition, spatio-temporal features from different modalities are used for recognizing activities. Temporal modeling is a long challenge of action recognition. However, there are limited methods such as pre-computed…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Elham Shabaninia , Hossein Nezamabadi-pour , Fatemeh Shafizadegan