Related papers: Simple vs complex temporal recurrences for video s…
Despite the notable advancements in numerous Transformer-based models, the task of long multi-horizon time series forecasting remains a persistent challenge, especially towards explainability. Focusing on commonly used saliency maps in…
Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we…
The performance of convolutional neural networks has continued to improve over the last decade. At the same time, as model complexity grows, it becomes increasingly more difficult to explain model decisions. Such explanations may be of…
With recent advances in deep learning, neuroimaging studies increasingly rely on convolutional networks (ConvNets) to predict diagnosis based on MR images. To gain a better understanding of how a disease impacts the brain, the studies…
To detect salient objects accurately, existing methods usually design complex backbone network architectures to learn and fuse powerful features. However, the saliency inference module that performs saliency prediction from the fused…
Salient object detection is subjective in nature, which implies that multiple estimations should be related to the same input image. Most existing salient object detection models are deterministic following a point to point estimation…
There has been profound progress in visual saliency thanks to the deep learning architectures, however, there still exist three major challenges that hinder the detection performance for scenes with complex compositions, multiple salient…
The Transformer architecture has gained significant popularity in computer vision tasks due to its capacity to generalize and capture long-range dependencies. This characteristic makes it well-suited for generating spatiotemporal tokens…
We introduce MinConvLSTM and MinConvGRU, two novel spatiotemporal models that combine the spatial inductive biases of convolutional recurrent networks with the training efficiency of minimal, parallelizable RNNs. Our approach extends the…
In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is…
We present a new architecture for end-to-end sequence learning of actions in video, we call VideoLSTM. Rather than adapting the video to the peculiarities of established recurrent or convolutional architectures, we adapt the architecture to…
Efficient video recognition is a hot-spot research topic with the explosive growth of multimedia data on the Internet and mobile devices. Most existing methods select the salient frames without awareness of the class-specific saliency…
Benefiting from deep learning research and large-scale datasets, saliency prediction has achieved significant success in the past decade. However, it still remains challenging to predict saliency maps on images in new domains that lack…
Predicting attention is a popular topic at the intersection of human and computer vision. However, even though most of the available video saliency data sets and models claim to target human observers' fixations, they fail to differentiate…
Temporally locating and classifying action segments in long untrimmed videos is of particular interest to many applications like surveillance and robotics. While traditional approaches follow a two-step pipeline, by generating frame-wise…
This study proposes a multi-resolution Convolutional Long Short-Term Memory (ConvLSTM) ensemble framework that leverages diverse temporal input resolutions to mitigate error accumulation and improve long-horizon forecasting of…
In this paper, we propose several novel deep learning methods for object saliency detection based on the powerful convolutional neural networks. In our approach, we use a gradient descent method to iteratively modify an input image based on…
Domain alignment in convolutional networks aims to learn the degree of layer-specific feature alignment beneficial to the joint learning of source and target datasets. While increasingly popular in convolutional networks, there have been no…
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open…
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain. By focusing on the benefits of joint auditory and visual information, most VSP methods are capable of…