Related papers: Vision Augmentation Prediction Autoencoder with At…
This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that employ neural rendering with explicit depth supervision,…
The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…
We present a method to improve video description generation by modeling higher-order interactions between video frames and described concepts. By storing past visual attention in the video associated to previously generated words, the…
Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent…
Anticipating future actions based on spatiotemporal observations is essential in video understanding and predictive computer vision. Moreover, a model capable of anticipating the future has important applications, it can benefit…
We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…
Video anomaly detection is a subject of great interest across industrial and academic domains due to its crucial role in computer vision applications. However, the inherent unpredictability of anomalies and the scarcity of anomaly samples…
Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information.…
Advancements in attention mechanisms have led to significant performance improvements in a variety of areas in machine learning due to its ability to enable the dynamic modeling of temporal sequences. A particular area in computer vision…
Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…
3D convolutional neural networks have achieved promising results for video tasks in computer vision, including video saliency prediction that is explored in this paper. However, 3D convolution encodes visual representation merely on fixed…
Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…
Currently successful methods for video description are based on encoder-decoder sentence generation using recur-rent neural networks (RNNs). Recent work has shown the advantage of integrating temporal and/or spatial attention mechanisms…
Visual Attention Prediction (VAP) is a significant and imperative issue in the field of computer vision. Most of existing VAP methods are based on deep learning. However, they do not fully take advantage of the low-level contrast features…
Various Vision Transformer (ViT) models have been widely used for image recognition tasks. However, existing visual explanation methods can not display the attention flow hidden inside the inner structure of ViT models, which explains how…
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…
Due to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP). To address this issue, we develop an effective spatiotemporal…
The existing state-of-the-art method for audio-visual conditioned video prediction uses the latent codes of the audio-visual frames from a multimodal stochastic network and a frame encoder to predict the next visual frame. However, a direct…
This paper outlines the development and testing of a novel, feedback-enabled attention allocation aid (AAAD), which uses real-time physiological data to improve human performance in a realistic sequential visual search task. Indeed, by…
Unsupervised multivariate time series anomaly detection (UMTSAD) plays a critical role in various domains, including finance, networks, and sensor systems. In recent years, due to the outstanding performance of deep learning in general…