Related papers: DMAT: A Dynamic Mask-Aware Transformer for Human D…

Although many approaches for multi-human pose estimation in videos have shown profound results, they require densely annotated data which entails excessive man labor. Furthermore, there exists occlusion and motion blur that inevitably lead…

Person re-identification (re-ID) continues to pose a significant challenge, particularly in scenarios involving occlusions. Prior approaches aimed at tackling occlusions have predominantly focused on aligning physical body features through…

Almost all existing amodal segmentation methods make the inferences of occluded regions by using features corresponding to the whole image. This is against the human's amodal perception, where human uses the visible part and the shape prior…

Human pose estimation aims to figure out the keypoints of all people in different scenes. Current approaches still face some challenges despite promising results. Existing top-down methods deal with a single person individually, without the…

Predicting pedestrian crossing intentions is crucial for the navigation of mobile robots and intelligent vehicles. Although recent deep learning-based models have shown significant success in forecasting intentions, few consider incomplete…

To fully understand the 3D context of a single image, a visual system must be able to segment both the visible and occluded regions of objects, while discerning their occlusion order. Ideally, the system should be able to handle any object…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views. Many methods use the background as artificial occlusion and rely on…

Humans inherently possess generalizable visual representations that empower them to efficiently explore and interact with the environments in manipulation tasks. We advocate that such a representation automatically arises from…

Image anomaly detection consists in detecting images or image portions that are visually different from the majority of the samples in a dataset. The task is of practical importance for various real-life applications like biomedical image…

Human mesh reconstruction from a single image is challenging in the presence of occlusion, which can be caused by self, objects, or other humans. Existing methods either fail to separate human features accurately or lack proper supervision…

Transformer is an attention-based neural network, which consists of two sublayers, namely, Self-Attention Network (SAN) and Feed-Forward Network (FFN). Existing research explores to enhance the two sublayers separately to improve the…

Action recognition technology plays a vital role in enhancing security through surveillance systems, enabling better patient monitoring in healthcare, providing in-depth performance analysis in sports, and facilitating seamless human-AI…

Though image transformers have shown competitive results with convolutional neural networks in computer vision tasks, lacking inductive biases such as locality still poses problems in terms of model efficiency especially for embedded…

Face filters have become a key element of short-form video content, enabling a wide array of visual effects such as stylization and face swapping. However, their performance often degrades in the presence of occlusions, where objects like…

In this paper a doubly attentive transformer machine translation model (DATNMT) is presented in which a doubly-attentive transformer decoder normally joins spatial visual features obtained via pretrained convolutional neural networks,…

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

Traditionally, video conferencing is a widely adopted solution for telecommunication, but a lack of immersiveness comes inherently due to the 2D nature of facial representation. The integration of Virtual Reality (VR) in a…

The recovery of occluded human meshes presents challenges for current methods due to the difficulty in extracting effective image features under severe occlusion. In this paper, we introduce DPMesh, an innovative framework for occluded…

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only…