Spatiotemporal Saliency in Dynamic Scenes

By Vijay Mahadevan, Nuno Vasconcelos. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010

437 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/62eb421cdac9de9255578f14fba55146d958be44

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

ViBe: A Universal Background Subtraction Algorithm for Video Sequences (2011, background): “The authors of [19] were inspired by the biological mechanism of motion-based perceptual grouping.”
Revisiting Video Saliency Prediction in the Deep Learning Era (2021, background): “Some of these studies [11], [58], [59] can be viewed as extensions of existing static saliency models with additional motion features.”
Video Processing From Electro-Optical Sensors for Object Detection and Tracking in a Maritime Environment: A Survey (2016, methodology): “Mahadevan and Vasconcelos [152] combined the discriminant saliency approach of [151] and mixture of dynamic textures [142] for determining spatially normal (high probability distributions) and temporally normal (high probability events) features of the videos with the moving crowd in urban scenarios”
Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement (2015, methodology): “Similarly, Mahadevan and Vasconcelos [8] combined center-surround saliency with the dynamic textures for spatiotemporal saliency using the saliency model in [6].”
Saliency-aware geodesic video object segmentation (2015, background): “These saliency methods [14, 20, 28, 26, 13, 21], however, usually build their system as a simple combination of existing image saliency models with motion cues.”
State-of-the-Art in Visual Attention Modeling (2013, background): “Gao and Vasconcelos [146] argued that for recognition, salient features are those that best distinguish a class of interest from all other visual classes.”
Visual Saliency Based on Scale-Space Analysis in the Frequency Domain (2013, neutral): “F”
Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (2018, background): “Some of those studies [14, 41, 52] can be viewed as extensions of exiting static saliency models with additional motion features.”
Coupled ensemble graph cuts and object verification for animal segmentation from highly cluttered videos (2015, neutral): “However, the availability of methods that are robust and generic enough to handle the complexities of most natural dynamic scenes is still very limited [7] [8].”
Ensemble Video Object Cut in Highly Dynamic Scenes (2013, methodology): “The data used for our performance evaluation consists of existing benchmark datasets and our in-house wildlife monitoring videos: (A) WavingTrees [25]; (B) Fountain [23]; (C) Combination with 9 complex scenes [13, 12]; (D) WaterObject with a jug floating on the rippling water [27]; (E) RainCar with ”
Gaze Prediction in Dynamic 360° Immersive Videos (2018, background): “Some work also attempts to use low-level appearance and motion cues as inputs or extend deep learning approaches to more complex scenarios such as stereo images [9] or videos [4] [7] [11] [31] [35] [32] [16] [12] [6] [18].”
Video Salient Object Detection via Fully Convolutional Networks (2017, background): “Early models [52]–[54] can be viewed as simple extensions of exiting static saliency models with extra temporal dimension.”
Camera-trap images segmentation using multi-layer robust principal component analysis (2017, background): “Nevertheless, there are not enough methods that can handle the complexity of natural dynamic scenes [5].”
Saliency-Aware Video Object Segmentation (2018, methodology): “Similarly, Mahadevan et al. [14] combined center-surround saliency with dynamic textures for spatiotemporal saliency using the saliency model in [47].”