Presented at the European Conference on Computer Vision (ECCV) 2020. R. Droste and J. Jiao contributed equally to this work. v3: Updated Fig. 5a) and added new MTI300 benchmark results to supp. material
Visual saliency modeling for images and videos is treated as two independent tasks in recent computer vision literature. While image saliency modeling is a well-studied problem and progress on benchmarks like SALICON and MIT300 is slowing, video saliency models have shown rapid gains on the recent DHF1K benchmark. Here, we take a step back and ask: Can image and video saliency modeling be approached via a unified model, with mutual benefit? We identify different sources of domain shift between image and video saliency data and between different video saliency datasets as a key challenge for effective joint modelling. To address this we propose four novel domain adaptation techniques - Domain-Adaptive Priors, Domain-Adaptive Fusion, Domain-Adaptive Smoothing and Bypass-RNN - in addition to an improved formulation of learned Gaussian priors. We integrate these techniques into a simple and lightweight encoder-RNN-decoder-style network, UNISAL, and train it jointly with image and video saliency data. We evaluate our method on the video saliency datasets DHF1K, Hollywood-2 and UCF-Sports, and the image saliency datasets SALICON and MIT300. With one set of parameters, UNISAL achieves state-of-the-art performance on all video saliency datasets and is on par with the state-of-the-art for image saliency datasets, despite faster runtime and a 5 to 20-fold smaller model size compared to all competing deep methods. We provide retrospective analyses and ablation studies which confirm the importance of the domain shift modeling. The code is available at https://github.com/rdroste/unisal
Insight Centre for Data Analytics, Dublin City University（都柏林城市大学Insight数据分析中心）；Institut National des Télécommunications et des TIC（国家电信与信息通信技术学院）
The spherical domain representation of 360 video/image presents many challenges related to the storage, processing, transmission and rendering of omnidirectional videos (ODV). Models of human visual attention can be used so that only a single viewport is rendered at a time, which is important when developing systems that allow users to explore ODV with head mounted displays (HMD). Accordingly, researchers have proposed various saliency models for 360 video/images. This paper proposes ATSal, a novel attention based (head-eye) saliency model for 360\degree videos. The attention mechanism explici…
We tackle the problem of predicting saliency maps for videos of dynamic scenes. We note that the accuracy of the maps reconstructed from the gaze data of a fixed number of observers varies with the frame, as it depends on the content of the scene. This issue is particularly pressing when a limited number of observers are available. In such cases, directly minimizing the discrepancy between the predicted and measured saliency maps, as traditional deep-learning methods do, results in overfitting to the noisy data. We propose a noise-aware training (NAT) paradigm that quantifies and accounts for …
Temporal Saliency-Guided Distillation: A Scalable Framework for Distilling Video Datasets
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Shanghai Jiao Tong University（上海交通大学）
In this paper, we address the problem of quantifying reliability of computational saliency for videos, which can be used to improve saliency-based video processing and enable more reliable performance and risk assessment of such processing. Our approach is twofold. First, we explore spatial correlations in both saliency map and eye-fixation map. Then, we learn spatiotemporal correlations that define a reliable saliency map. We first study spatiotemporal eye-fixation data from a public dataset and investigate a common feature in human visual attention, which dictates correlation in saliency bet…
Beijing Institute of Technology（北京理工大学）；Nankai University（南开大学）；University of Central Florida（中佛罗里达大学）
In this work, we contribute to video saliency research in two ways. First, we introduce a new benchmark for predicting human eye movements during dynamic scene free-viewing, which is long-time urged in this field. Our dataset, named DHF1K (Dynamic Human Fixation), consists of 1K high-quality, elaborately selected video sequences spanning a large range of scenes, motions, object types and background complexity. Existing video saliency datasets lack variety and generality of common dynamic scenes and fall short in covering challenging situations in unconstrained environments. In contrast, DHF1K …
As an emerging vision platform, a drone can look from many abnormal viewpoints which brings many new challenges into the classic vision task of video saliency prediction. To investigate these challenges, this paper proposes a large-scale video dataset for aerial saliency prediction, which consists of ground-truth salient object regions of 1,000 aerial videos, annotated by 24 subjects. To the best of our knowledge, it is the first large-scale video dataset that focuses on visual saliency prediction on drones. Based on this dataset, we propose a Model-guided Multi-path Network (MM-Net) that serv…
Beihang University（北京航空航天大学）；Peng Cheng Laboratory（鹏城实验室）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational capability and storage space so that the direct deployment of complex deep saliency models becomes infeasible. To address this problem, this paper proposes a dynamic saliency estimation approach for aerial videos via spatiotemporal knowledge distillation. In this approach, five components are involved, including two teachers, two students and the desired spatiot…
University of Science and Technology of China（中国科学技术大学）；XI’AN University of Posts & Telecommunications（西安邮电大学）
Video smoke detection is a promising fire detection method especially in open or large spaces and outdoor environments. Traditional video smoke detection methods usually consist of candidate region extraction and classification, but lack powerful characterization for smoke. In this paper, we propose a novel video smoke detection method based on deep saliency network. Visual saliency detection aims to highlight the most important object regions in an image. The pixel-level and object-level salient convolutional neural networks are combined to extract the informative smoke saliency map. An end-t…
Insight SFI Research Centre for Data Analytics（Insight SFI数据分析研究中心）；Dublin City University（都柏林城市大学）；University of Catania（卡塔尼亚大学）
Video saliency prediction has recently attracted attention of the research community, as it is an upstream task for several practical applications. However, current solutions are particularly computationally demanding, especially due to the wide usage of spatio-temporal 3D convolutions. We observe that, while different model architectures achieve similar performance on benchmarks, visual variations between predicted saliency maps are still significant. Inspired by this intuition, we propose a lightweight model that employs multiple simple heterogeneous decoders and adopts several practical app…
OpenSAL360: Open-Source Crowdsourcing Platform for Omnidirectional Video Saliency Collection
AI Center, Lomonosov Moscow State University（莫斯科国立大学人工智能中心）；MSU Institute for Artificial Intelligence（莫斯科国立大学人工智能研究所）；Lomonosov Moscow State University（莫斯科国立大学）
National Tsing Hua University（国立清华大学）；Taiwan AI Labs（台湾人工智能实验室）；Academia Sinica（中央研究院）
Automatic saliency prediction in 360° videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). We propose a spatial-temporal network which is (1) weakly-supervised trained and (2) tailor-made for 360° viewing sphere. Note that most existing methods are less scalable since they rely on annotated saliency map for training. Most importantly, they convert 360° sphere to 2D images (e.g., a single equirectangular image or multiple separate Normal Field-of-View (NFoV) images) which introduces distortion and image boundaries. In contrast, we propose a simple and effective Cub…
National University of Sciences and Technology (NUST)（国立科技大学（NUST））
Understanding human visual attention and saliency is an integral part of vision research. In this context, there is an ever-present need for fresh and diverse benchmark datasets, particularly for insight into special use cases like crowded scenes. We contribute to this end by: (1) reviewing the dynamics behind saliency and crowds. (2) using eye tracking to create a dynamic human eye fixation dataset over a new set of crowd videos gathered from the Internet. The videos are annotated into three distinct density levels. (3) Finally, we evaluate state-of-the-art saliency models on our dataset to i…
Predicting saliency in videos is a challenging problem due to complex modeling of interactions between spatial and temporal information, especially when ever-changing, dynamic nature of videos is considered. Recently, researchers have proposed large-scale datasets and models that take advantage of deep learning as a way to understand what's important for video saliency. These approaches, however, learn to combine spatial and temporal features in a static manner and do not adapt themselves much to the changes in the video content. In this paper, we introduce Gated Fusion Network for dynamic sal…
In this paper, we present an analysis of recorded eye-fixation data from human subjects viewing video sequences. The purpose is to better understand visual attention for videos. Utilizing the eye-fixation data provided in the CRCNS (Collaborative Research in Computational Neuroscience) dataset, this paper focuses on the relation between the saliency of a pixel and that of its direct neighbors, without making any assumption about the structure of the eye-fixation maps. By employing some basic concepts from information theory, the analysis shows substantial correlation between the saliency of a …
Shanghai Institute for Advanced Communication and Data Science, Shanghai University（上海大学上海先进通信与数据科学研究院）；School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；Department of Computer Science, University of Manitoba（曼尼托巴大学计算机科学系）；Shanghai Key Laboratory of Psychotic Disorders, Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine（上海交通大学医学院附属精神卫生中心上海市精神病重点实验室）
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 local spacetime according to its kernel size, while human attention is always attracted by relational visual features at different time. To overcome this limitation, we propose a novel Spatio-Temporal Self-Attention 3D Network (STSANet) for video saliency prediction, in which multiple Spatio-Temporal Self-Attention (STSA) modules are employed at different lev…
School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）；Inception Institute of Artificial Intelligence（Inception人工智能研究所）；School of Computer and Control Engineering, Nankai University（南开大学计算机与控制工程学院）；School of Computer Science Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）；School of Computer and Control Engineering, University of Chinese Academy of Sciences（中国科学院大学计算机与控制工程学院）
Visual saliency detection model simulates the human visual system to perceive the scene, and has been widely used in many vision tasks. With the acquisition technology development, more comprehensive information, such as depth cue, inter-image correspondence, or temporal relationship, is available to extend image saliency detection to RGBD saliency detection, co-saliency detection, or video saliency detection. RGBD saliency detection model focuses on extracting the salient regions from RGBD images by combining the depth information. Co-saliency detection model introduces the inter-image corres…
SOTA: Spike-Navigated Optimal TrAnsport Saliency Region Detection in Composite-bias Videos
State Key Laboratory for Multimedia Information Processing（多媒体信息处理国家重点实验室）；Hubei Key Laboratory of Transportation Internet of Things（湖北省交通运输物联网重点实验室）；Institute for Artificial Intelligence（人工智能研究院）
Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360-Degree Videos
Department of Computer Science and Engineering, Koç University（计算机科学与工程系，科克大学）；Department of Psychology, Boğaziçi University（心理学系，博多伊大学）；National Institute of Advanced Industrial Science and Technology (AIST), Intelligent Platforms Research Institute（国家先进工业科学与技术研究院（AIST），智能平台研究机构）；Department of Psychology, Boğaziçi University University（心理学系，博多伊大学）；Department of Computer Engineering, Hacettepe University（计算机工程系，哈切塞特佩大学）；KUIS AI Center（KUIS人工智能中心）
STMicrolectronics, ADG Central R&D, Catania, Italy（意法半导体，ADG中央研发部，卡塔尼亚，意大利）；PeRCeiVe Lab - University of Catania（PeRCeiVe实验室 - 卡塔尼亚大学）
In this work, we propose a 3D fully convolutional architecture for video saliency prediction that employs hierarchical supervision on intermediate maps (referred to as conspicuity maps) generated using features extracted at different abstraction levels. We provide the base hierarchical learning mechanism with two techniques for domain adaptation and domain-specific learning. For the former, we encourage the model to unsupervisedly learn hierarchical general features using gradient reversal at multiple scales, to enhance generalization capabilities on datasets for which no annotations are provi…
Nanjing University of Information Science and Technology（南京信息工程大学）；JD Finance America Corporation（京东金融美国公司）
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 feature alignment network tailored to VSP, mainly including two key sub-networks: a multi-scale deformable convolutional alignment network (MDAN) and a bidirectional convolutional Long Short-Term Memory (Bi-ConvLSTM) network. The MDAN learns to align the features of the neighboring frames to the reference one in a coarse-to-fine manner, which can well handle v…
Shanghai Jiao Tong University（上海交通大学）；Beijing University of Technology（北京工业大学）；University of Macau（澳门大学）
Augmented reality (AR) overlays digital content onto the reality. In AR system, correct and precise estimations of user's visual fixations and head movements can enhance the quality of experience by allocating more computation resources on the areas of interest. However, there is inadequate research about understanding the visual exploration of users when using an AR system or modeling AR visual attention. To bridge the gap between the saliency prediction on real-world scene and on scene augmented by virtual information, we construct the ARVR saliency dataset with 12 diverse videos viewed by 2…
University of Barcelona（巴塞罗那大学）；University of Tübingen（图宾根大学）
Since 2014 transfer learning has become the key driver for the improvement of spatial saliency prediction; however, with stagnant progress in the last 3-5 years. We conduct a large-scale transfer learning study which tests different ImageNet backbones, always using the same read out architecture and learning protocol adopted from DeepGaze II. By replacing the VGG19 backbone of DeepGaze II with ResNet50 features we improve the performance on saliency prediction from 78% to 85%. However, as we continue to test better ImageNet models as backbones (such as EfficientNetB5) we observe no additional …
University of Wisconsin - Milwaukee（威斯康星大学密尔沃基分校）；University of Southern California（南加州大学）
Saliency modeling has been an active research area in computer vision for about two decades. Existing state of the art models perform very well in predicting where people look in natural scenes. There is, however, the risk that these models may have been overfitting themselves to available small scale biased datasets, thus trapping the progress in a local minimum. To gain a deeper insight regarding current issues in saliency modeling and to better gauge progress, we recorded eye movements of 120 observers while they freely viewed a large number of naturalistic and artificial images. Our stimul…
This paper addresses the challenging problem of estimating the general visual attention of people in images. Our proposed method is designed to work across multiple naturalistic social scenarios and provides a full picture of the subject's attention and gaze. In contrast, earlier works on gaze and attention estimation have focused on constrained problems in more specific contexts. In particular, our model explicitly represents the gaze direction and handles out-of-frame gaze targets. We leverage three different datasets using a multi-task learning approach. We evaluate our method on widely use…
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；CiTIUS（CiTIUS（圣地亚哥德孔波斯特拉大学智能技术研究中心））；Universidade de Santiago de Compostela（圣地亚哥德孔波斯特拉大学）
A benchmark of saliency models performance with a synthetic image dataset is provided. Model performance is evaluated through saliency metrics as well as the influence of model inspiration and consistency with human psychophysics. SID4VAM is composed of 230 synthetic images, with known salient regions. Images were generated with 15 distinct types of low-level features (e.g. orientation, brightness, color, size...) with a target-distractor pop-out type of synthetic patterns. We have used Free-Viewing and Visual Search task instructions and 7 feature contrasts for each feature category. Our stud…
RGB-D salient object detection (SOD) is usually formulated as a problem of classification or regression over two modalities, i.e., RGB and depth. Hence, effective RGBD feature modeling and multi-modal feature fusion both play a vital role in RGB-D SOD. In this paper, we propose a depth-sensitive RGB feature modeling scheme using the depth-wise geometric prior of salient objects. In principle, the feature modeling scheme is carried out in a depth-sensitive attention module, which leads to the RGB feature enhancement as well as the background distraction reduction by capturing the depth geometry…
Multi-level features are important for saliency detection. Better combination and use of multi-level features with time information can greatly improve the accuracy of the video saliency model. In order to fully combine multi-level features and make it serve the video saliency model, we propose a 3D fully convolutional encoder-decoder architecture for video saliency detection, which combines scale, space and time information for video saliency modeling. The encoder extracts multi-scale temporal-spatial features from the input continuous video frames, and then constructs temporal-spatial featur…
Insight Center for Data Analytics（Insight数据分析中心）；Dublin City University（都柏林城市大学）；Universitat Politecnica de Catalunya（加泰罗尼亚理工大学）
This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain. The first modification is the addition of a ConvLSTM within the architecture, while the second is a conceptually simple exponential moving average of an internal convolutional state. We use weights pre-trained on the SALICON dataset and fine-tune our model on DHF1K. Our results show that both modifications achieve state-of-the-art results and produce similar saliency maps. Source code is available at https:/…
Jiangxi University of Finance and Economics（江西财经大学）
Different from salient object detection methods for still images, a key challenging for video saliency detection is how to extract and combine spatial and temporal features. In this paper, we present a novel and effective approach for salient object detection for video sequences based on 3D convolutional neural networks. First, we design a 3D convolutional network (Conv3DNet) with the input as three video frame to learn the spatiotemporal features for video sequences. Then, we design a 3D deconvolutional network (Deconv3DNet) to combine the spatiotemporal features to predict the final saliency…
Beijing Institute of Technology（北京理工大学）；University of East Anglia（东安格利亚大学）
This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: (1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data, and (2) fast video saliency training and detection. The proposed deep video saliency network consists of two modules, for capturing the spatial and temporal saliency information, respectively. The dynamic saliency model, explicitly incorporating saliency estimates from the static saliency model, directly produces spatiotemporal saliency inference without ti…
As an important and challenging problem in computer vision, video saliency detection is typically cast as a spatiotemporal context modeling problem over consecutive frames. As a result, a key issue in video saliency detection is how to effectively capture the intrinsical properties of atomic video structures as well as their associated contextual interactions along the spatial and temporal dimensions. Motivated by this observation, we propose a graph-theoretic video saliency detection approach based on adaptive video structure discovery, which is carried out within a spatiotemporal atomic grap…
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；Qingdao University（青岛大学）；Peng Cheng Laboratory（鹏城实验室）；Stony Brook University（石溪大学）
With the rapid development of deep learning techniques, image saliency deep models trained solely by spatial information have occasionally achieved detection performance for video data comparable to that of the models trained by both spatial and temporal information. However, due to the lesser consideration of temporal information, the image saliency deep models may become fragile in the video sequences dominated by temporal information. Thus, the most recent video saliency detection approaches have adopted the network architecture starting with a spatial deep model that is followed by an elab…
In this paper we introduce a novel Depth-Aware Video Saliency approach to predict human focus of attention when viewing RGBD videos on regular 2D screens. We train a generative convolutional neural network which predicts a saliency map for a frame, given the fixation map of the previous frame. Saliency estimation in this scenario is highly important since in the near future 3D video content will be easily acquired and yet hard to display. This can be explained, on the one hand, by the dramatic improvement of 3D-capable acquisition equipment. On the other hand, despite the considerable progress…
Universitat Politecnica de Catalunya（加泰罗尼亚理工大学）；Dublin City University（都柏林城市大学）
This work adapts a deep neural model for image saliency prediction to the temporal domain of egocentric video. We compute the saliency map for each video frame, firstly with an off-the-shelf model trained from static images, secondly by adding a a convolutional or conv-LSTM layers trained with a dataset for video saliency prediction. We study each configuration on EgoMon, a new dataset made of seven egocentric videos recorded by three subjects in both free-viewing and task-driven set ups. Our results indicate that the temporal adaptation is beneficial when the viewer is not moving and observin…
Over the past few years, deep neural networks (DNNs) have exhibited great success in predicting the saliency of images. However, there are few works that apply DNNs to predict the saliency of generic videos. In this paper, we propose a novel DNN-based video saliency prediction method. Specifically, we establish a large-scale eye-tracking database of videos (LEDOV), which provides sufficient data to train the DNN models for predicting video saliency. Through the statistical analysis of our LEDOV database, we find that human attention is normally attracted by objects, particularly moving objects…
ViASNet: A Video Ad Saliency Network for Predicting Dynamic Saliency and Viewer Engagement
Department of Mathematics, University of Maryland, College Park, MD 20742, USA（数学系，马里兰大学，学院公园，MD 20742, 美国）；Robert H. Smith School of Business, University of Maryland, College Park, MD 20742, USA（罗伯特·H·史密斯商学院，马里兰大学，学院公园，MD 20742, 美国）
National University of Sciences and Technology（国立科技大学）；School of Electrical Engineering and Computer Science（电气工程与计算机科学学院）
Substantial research has been done in saliency modeling to develop intelligent machines that can perceive and interpret their surroundings. But existing models treat videos as merely image sequences excluding any audio information, unable to cope with inherently varying content. Based on the hypothesis that an audiovisual saliency model will be an improvement over traditional saliency models for natural uncategorized videos, this work aims to provide a generic audio/video saliency model augmenting a visual saliency map with an audio saliency map computed by synchronizing low-level audio and vi…
SOKENDAI (Graduate University for Advanced Studies)（综合研究大学院大学）；National Institute of Informatics（国立信息学研究所）
Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and dynamic features computed from the low and middle levels are combined together. Our method utilizes such combined features spatially over each frame and, at the same time, temporally across frames using consistency between consecutive frames. Saliency cues in our method are analyzed through a multiscale segmentation model, and fused across scale levels, yiel…
University of Science and Technology of China（中国科学技术大学）；Capital Normal University（首都师范大学）
Person re-identification aims at identifying a certain pedestrian across non-overlapping camera networks. Video-based re-identification approaches have gained significant attention recently, expanding image-based approaches by learning features from multiple frames. In this work, we propose a novel Co-Saliency Spatio-Temporal Interaction Network (CSTNet) for person re-identification in videos. It captures the common salient foreground regions among video frames and explores the spatial-temporal long-range context interdependency from such regions, towards learning discriminative pedestrian rep…
TASED-Net is a 3D fully-convolutional network architecture for video saliency detection. It consists of two building blocks: first, the encoder network extracts low-resolution spatiotemporal features from an input clip of several consecutive frames, and then the following prediction network decodes the encoded features spatially while aggregating all the temporal information. As a result, a single prediction map is produced from an input clip of multiple frames. Frame-wise saliency maps can be predicted by applying TASED-Net in a sliding-window fashion to a video. The proposed approach assumes…
ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction
Shandong University（山东大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；City University of Hong Kong（香港城市大学）；Shenzhen Loop Area Institute（深圳河套学院）
360$^\circ$ video saliency detection is one of the challenging benchmarks for 360$^\circ$ video understanding since non-negligible distortion and discontinuity occur in the projection of any format of 360$^\circ$ videos, and capture-worthy viewpoint in the omnidirectional sphere is ambiguous by nature. We present a new framework named Panoramic Vision Transformer (PAVER). We design the encoder using Vision Transformer with deformable convolution, which enables us not only to plug pretrained models from normal videos into our architecture without additional modules or finetuning but also to per…
