Related papers: Combined CNN Transformer Encoder for Enhanced Fine…

In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to…

We propose an end-to-end learned image compression codec wherein the analysis transform is jointly trained with an object classification task. This study affirms that the compressed latent representation can predict human perceptual…

Fine-grained classification is a relatively new field that has concentrated on using information from a single image, while ignoring the enormous potential of using video data to improve classification. In this work we present the novel…

Foundation models (FMs) are large neural networks trained on broad datasets, excelling in downstream tasks with minimal fine-tuning. Human activity recognition in video has advanced with FMs, driven by competition among different…

Recently, referring image segmentation has aroused widespread interest. Previous methods perform the multi-modal fusion between language and vision at the decoding side of the network. And, linguistic feature interacts with visual feature…

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…

In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from…

Image animation aims to animate a source image by using motion learned from a driving video. Current state-of-the-art methods typically use convolutional neural networks (CNNs) to predict motion information, such as motion keypoints and…

Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based…

Recognizing human actions in adverse lighting conditions presents significant challenges in computer vision, with wide-ranging applications in visual surveillance and nighttime driving. Existing methods tackle action recognition and dark…

This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations…

Deep learning, e.g., convolutional neural networks (CNNs), has achieved great success in image processing and computer vision especially in high level vision applications such as recognition and understanding. However, it is rarely used to…

Scene text recognition, as a cross-modal task involving vision and text, is an important research topic in computer vision. Most existing methods use language models to extract semantic information for optimizing visual recognition.…

Convolutional Neural Networks (CNNs) are used for a wide range of image-related tasks such as image classification and object detection. However, a large pre-trained CNN model contains a lot of redundancy considering the task-specific edge…

The Convolutional Neural Network (CNN) has been the dominant image feature extractor in computer vision for years. However, it fails to get the relationship between images/objects and their hierarchical interactions which can be helpful for…

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring…

Fine-grained action segmentation and recognition is an important yet challenging task. Given a long, untrimmed sequence of kinematic data, the task is to classify the action at each time frame and segment the time series into the correct…

The perceptual-based grouping process produces a hierarchical and compositional image representation that helps both human and machine vision systems recognize heterogeneous visual concepts. Examples can be found in the classical…

Visual saliency prediction using transformers - Convolutional neural networks (CNNs) have significantly advanced computational modelling for saliency prediction. However, accurately simulating the mechanisms of visual attention in the human…

Temporal modeling still remains challenging for action recognition in videos. To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal…