English
Related papers

Related papers: Hint: hierarchical inter-frame correlation for one…

200 papers

Point clouds have attracted increasing attention. Significant progress has been made in methods for point cloud analysis, which often requires costly human annotation as supervision. To address this issue, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Bi'an Du , Xiang Gao , Wei Hu , Xin Li

We propose an end-to-end trainable image compression framework with a multi-scale and context-adaptive entropy model, especially for low bitrate compression. Due to the success of autoregressive priors in probabilistic generative model, the…

Image and Video Processing · Electrical Eng. & Systems 2019-10-18 Jing Zhou , Sihan Wen , Akira Nakagawa , Kimihiko Kazui , Zhiming Tan

Visual Language Models require substantial computational resources for inference due to the additional input tokens needed to represent visual information. However, these visual tokens often contain redundant and unimportant information,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Mohamed Dhouib , Davide Buscaldi , Sonia Vanier , Aymen Shabou

Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline.…

Machine Learning · Computer Science 2019-05-08 Alex H. Lang , Sourabh Vora , Holger Caesar , Lubing Zhou , Jiong Yang , Oscar Beijbom

Large number of weights in deep neural networks makes the models difficult to be deployed in low memory environments such as, mobile phones, IOT edge devices as well as "inferencing as a service" environments on cloud. Prior work has…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-11-02 Dharma Teja Vooturi , Saurabh Goyal , Anamitra R. Choudhury , Yogish Sabharwal , Ashish Verma

This paper presents a cross channel context model for latents in deep image compression. Generally, deep image compression is based on an autoencoder framework, which transforms the original image to latents at the encoder and recovers the…

Image and Video Processing · Electrical Eng. & Systems 2021-03-05 Changyue Ma , Zhao Wang , Ruling Liao , Yan Ye

Learned image compression methods have shown superior rate-distortion performance and remarkable potential compared to traditional compression methods. Most existing learned approaches use stacked convolution or window-based self-attention…

Image and Video Processing · Electrical Eng. & Systems 2024-01-03 Huairui Wang , Nianxiang Fu , Zhenzhong Chen , Shan Liu

With the remarkable progress in neural P-frame video coding, neural B-frame coding has recently emerged as a critical research direction. However, most existing neural B-frame codecs directly adopt P-frame coding tools without adequately…

Image and Video Processing · Electrical Eng. & Systems 2026-02-24 Xihua Sheng , Peilin Chen , Meng Wang , Li Zhang , Shiqi Wang , Dapeng Oliver Wu

This paper develops a novel deep learning approach for solving evolutionary equations, which integrates sequential learning strategies with an enhanced hard constraint strategy featuring trainable parameters, addressing the low…

Machine Learning · Computer Science 2025-03-25 Yushi Zhang , Shuai Su , Yong Wang , Yanzhong Yao

Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Tuan-Anh Vu , Srinjay Sarkar , Zhiyuan Zhang , Binh-Son Hua , Sai-Kit Yeung

Understanding linguistics and morphology of resource-scarce code-mixed texts remains a key challenge in text processing. Although word embedding comes in handy to support downstream tasks for low-resource languages, there are plenty of…

Computation and Language · Computer Science 2021-06-01 Ayan Sengupta , Sourabh Kumar Bhattacharjee , Tanmoy Chakraborty , Md Shad Akhtar

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to…

Machine Learning · Computer Science 2026-01-16 Aryan Karmore

Recently, learned image compression has achieved remarkable performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in boosting rate-distortion performance. However, most entropy…

Image and Video Processing · Electrical Eng. & Systems 2024-09-16 Wei Jiang , Jiayu Yang , Yongqi Zhai , Peirong Ning , Feng Gao , Ronggang Wang

Representation learning using network embedding has received tremendous attention due to its efficacy to solve downstream tasks. Popular embedding methods (such as deepwalk, node2vec, LINE) are based on a neural architecture, thus unable to…

Social and Information Networks · Computer Science 2021-09-23 Debajyoti Bera , Rameshwar Pratap , Bhisham Dev Verma , Biswadeep Sen , Tanmoy Chakraborty

This study addresses the task of performing robust and reliable time-delay estimation in signals in noisy and reverberating environments. In contrast to the popular signal processing based methods, this paper proposes to transform the input…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Akshay Raina , Vipul Arora

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

Computation and Language · Computer Science 2026-04-21 Zhiyuan Shi , Qibo Qiu , Feng Xue , Zhonglin Jiang , Li Yu , Jian Jiang , Xiaofei He , Wenxiao Wang

In point cloud geometry compression, most octreebased context models use the cross-entropy between the onehot encoding of node occupancy and the probability distribution predicted by the context model as the loss. This approach converts the…

Image and Video Processing · Electrical Eng. & Systems 2024-07-12 Chang Sun , Hui Yuan , Xiaolong Mao , Xin Lu , Raouf Hamzaoui

Detecting transitions between intro/credits and main content in videos is a crucial task for content segmentation, indexing, and recommendation systems. Manual annotation of such transitions is labor-intensive and error-prone, while…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Vasilii Korolkov , Andrey Yanchenko

Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes. Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Mingfeng Zha , Tianyu Li , Guoqing Wang , Yunqiang Pei , Chaofan Qiao , Jiening Zhang , Yang Yang , Heng Tao Shen

Annotating large-scale point clouds is highly time-consuming and often infeasible for many complex real-world tasks. Point cloud pre-training has therefore become a promising strategy for learning discriminative representations without…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Guofeng Mei , Xiaoshui Huang , Juan Liu , Jian Zhang , Qiang Wu