Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-2

Gaze Prediction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in gaze-prediction-2

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find gaze-prediction-2 models and implementations

Datasets

GOO

OST

OpenEDS2020

EgoMon

EyeInfo

Subtasks

No subtasks available.

Most implemented papers

EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction

Damian Pascual, Roger Wattenhofer, Ard Kastrati, M. Płomecka, L. Wolf, Victor Gillioz, N. Langer•Fri Nov 05 2021

A new dataset and benchmark to evaluate gaze prediction from EEG measurements, consisting of simultaneous Electroencephalography and Eye-tracking recordings from 356 different subjects collected from three different experimental paradigms, is presented.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Faster gaze prediction with dense networks and Fisher pruning

Alykhan Tejani, Ferenc Huszár, Lucas Theis, I. Korshunova•Tue Jan 16 2018

Through a combination of knowledge distillation and Fisher pruning, this paper obtains much more runtime-efficient architectures for saliency prediction, achieving a 10x speedup for the same AUC performance as a state of the art network on the CAT2000 dataset.

224 0

Paper Graph

Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition

Yoichi Sato, Yifei Huang, Minjie Cai, Zhenqiang Li•Fri Mar 23 2018

A hybrid model based on deep neural networks which integrates task-dependent attention transition with bottom-up saliency prediction is proposed which significantly outperforms state-of-the-art gaze prediction methods and is able to learn meaningful transition of human attention.

150 0

Paper Graph

Deep Future Gaze: Gaze Anticipation on Egocentric Videos Using Adversarial Networks

Jiashi Feng, Mengmi Zhang, K. Ma, J. Lim, Qi Zhao•Fri Jun 30 2017

We introduce a new problem of gaze anticipation on egocentric videos. This substantially extends the conventional gaze prediction problem to future frames by no longer confining it on the current frame. To solve this problem, we propose a new generative adversarial neural network based model, Deep Future Gaze (DFG). DFG generates multiple future frames conditioned on the single current frame and anticipates corresponding future gazes in next few seconds. It consists of two networks: generator and discriminator. The generator uses a two-stream spatial temporal convolution architecture (3D-CNN) explicitly untangling the foreground and the background to generate future frames. It then attaches another 3D-CNN for gaze anticipation based on these synthetic frames. The discriminator plays against the generator by differentiating the synthetic frames of the generator from the real frames. Through competition with discriminator, the generator progressively improves quality of the future frames and thus anticipates future gaze better. Experimental results on the publicly available egocentric datasets show that DFG significantly outperforms all well-established baselines. Moreover, we demonstrate that DFG achieves better performance of gaze prediction on current frames than state-of-the-art methods. This is due to benefiting from learning motion discriminative representations in frame generation. We further contribute a new egocentric dataset (OST) in the object search task. DFG also achieves the best performance for this challenging dataset.

109 0

Paper Graph

GaTector: A Unified Framework for Gaze Object Prediction

Tao Hu, Binglu Wang, Baoshan Li, Xiaojuan Chen, Zhijie Zhang•Mon Dec 06 2021

A novel wUoC metric is proposed that can reveal the difference between boxes even when they share no overlapping area and is verification the superiority of the method in all three tracks, i.e. object detection, gaze estimation, and gaze object prediction.

43 0

Paper Graph

Gazing at Social Interactions Between Foraging and Decision Theory

Giuseppe Boccignone, Alessandro D'amelio•Mon Mar 29 2021

The audio-visual landscape of social interactions is distilled into a number of multimodal patches that convey different social value, and the general frame of foraging as a tradeoff between local patch exploitation and landscape exploration is worked under.

5 0

Paper Graph

Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention

D. Samaras, G. Zelinsky, Minh Hoai, Sounak Mondal, Zhibo Yang, Seoyoung Ahn•Sun Mar 26 2023

Gazeformer is a novel model that outperforms existing target-detection models on standard gaze prediction for both target- present and target-absent search tasks, and is more than five times faster than the state-of-the-art target-present visual search model.

45 0

Paper Graph

Adding a benchmark result helps the community track progress.

Gaze Prediction | State-of-the-Art