Related papers: Compact Generalized Non-local Network

We investigate the problem of representing an entire video using CNN features for human action recognition. Currently, limited by GPU memory, we have not been able to feed a whole video into CNN/RNNs for end-to-end learning. A common…

Motivated by the previous success of Two-Dimensional Convolutional Neural Network (2D CNN) on image recognition, researchers endeavor to leverage it to characterize videos. However, one limitation of applying 2D CNN to analyze videos is…

The non-local block is a popular module for strengthening the context modeling ability of a regular convolutional neural network. This paper first studies the non-local block in depth, where we find that its attention computation can be…

Compact neural networks are specially designed for applications on edge devices with faster inference speed yet modest performance. However, training strategies of compact models are borrowed from that of conventional models at present,…

Deep artificial neural networks have made remarkable progress in different tasks in the field of computer vision. However, the empirical analysis of these models and investigation of their failure cases has received attention recently. In…

Local-to-Nonlocal (LtN) coupling refers to a class of methods aimed at combining nonlocal and local modeling descriptions of a given system into a unified coupled representation. This allows to consolidate the accuracy of nonlocal models…

Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL…

Deep learning has been applied to compressive sensing (CS) of images successfully in recent years. However, existing network-based methods are often trained as the black box, in which the lack of prior knowledge is often the bottleneck for…

Graph neural networks are powerful architectures for structured datasets. However, current methods struggle to represent long-range dependencies. Scaling the depth or width of GNNs is insufficient to broaden receptive fields as larger GNNs…

Object detection, one of the three main tasks of computer vision, has been used in various applications. The main process is to use deep neural networks to extract the features of an image and then use the features to identify the class and…

Modern graph neural networks (GNNs) learn node embeddings through multilayer local aggregation and achieve great success in applications on assortative graphs. However, tasks on disassortative graphs usually require non-local aggregation.…

Deep neural networks have reached human-level performance on many computer vision tasks. However, the objectives used to train these networks enforce only that similar images are embedded at similar locations in the representation space,…

Nonlocal self-similarity (NSS) is an important prior that has been successfully applied in multi-dimensional data processing tasks, e.g., image and video recovery. However, existing NSS-based methods are solely suitable for meshgrid data…

Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which self-attention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention. In this…

The compressive sensing (CS) scheme exploits much fewer measurements than suggested by the Nyquist-Shannon sampling theorem to accurately reconstruct images, which has attracted considerable attention in the computational imaging community.…

Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the…

Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…

In the task of emotion recognition from videos, a key improvement has been to focus on emotions over time rather than a single frame. There are many architectures to address this task such as GRUs, LSTMs, Self-Attention, Transformers, and…

How do humans recognize an object in a piece of video? Due to the deteriorated quality of single frame, it may be hard for people to identify an occluded object in this frame by just utilizing information within one image. We argue that…

The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require…