EyeTAG: Eye Trajectory-Aware Gaze Estimation
arXiv:2610.00922v1 Announce Type: new Abstract: Gaze estimation under natural head-eye motion underpins applications from driver monitoring to human-computer interaction. Single-frame methods predict...
GazeFlow is a new framework for egocentric gaze prediction that models gaze as a joint distribution of temporal positions conditioned on both top‑down task cues and bottom‑up visual saliency. It employs conditional flow matching to iteratively transform Gaussian noise into realistic gaze trajectories, using a velocity field informed by video‑encoded visual features and global task queries. On standard benchmarks, GazeFlow outperforms existing methods on per‑frame metrics and produces trajectories that better reflect human gaze dynamics.
arXiv:2610.00922v1 Announce Type: new Abstract: Gaze estimation under natural head-eye motion underpins applications from driver monitoring to human-computer interaction. Single-frame methods predict...
StreamGaze is a new benchmark that evaluates how well Multimodal Large Language Models (MLLMs) use human gaze signals for temporal and proactive reasoning in streaming videos. It introduces gaze‑guided tasks covering past, present, and future responses, and employs a QA generation pipeline that aligns egocentric videos with raw gaze trajectories. The benchmark reveals significant gaps between current MLLMs and human performance, highlighting limitations in gaze‑based temporal reasoning, intent modeling, and proactive prediction.
arXiv:2610.28502v1 Announce Type: new Abstract: Smart glasses can help users understand their activities and surroundings, but small vision-language models must preserve useful evidence within limite...
EgoM2P is a masked‑modeling framework that learns from temporally‑aware multimodal tokens to train a large, general‑purpose model for egocentric 4D understanding. It supports multitasking across diverse egocentric perception and synthesis tasks—such as gaze prediction, egocentric camera tracking, monocular depth estimation, and conditional egocentric video synthesis—while matching or surpassing specialist models at a fraction of the computational cost. The authors plan to fully open‑source EgoM2P to advance egocentric vision research.
arXiv:2608.22926v1 Announce Type: new Abstract: Gaze is increasingly used as an input signal for vision and multimodal models, yet no consensus exists on how to represent it across datasets. Raw trac...
Gaze Attention is a new mechanism for multimodal large language models that selectively focuses on relevant visual regions during each generation step, rather than attending to all visual tokens. By grouping tokens into spatial regions and using learnable context tokens to retain global information, it reduces attention computation and visual key‑value entries by up to 90%. Experiments on 13 image and 6 video benchmarks show that Gaze Attention matches or outperforms dense‑attention baselines while using fewer visual resources.
arXiv:2211.11062v2 Announce Type: replace Abstract: Gaze following aims to predict where a person is looking in a scene, by predicting the target location, or indicating that the target is located ou...
arXiv:2610.08663v1 Announce Type: new Abstract: Video gaze prediction is led by gaze-trained models, yet gaze-free priors carry signal those models have not absorbed, if one knows when to trust them....
Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primarily employ brittle, multi-stage pipelines that require explicit inputs, like head bounding boxes and human pose, in order to identify the subject of gaze analysis.
arXiv:2609.05522v1 Announce Type: cross Abstract: Eye-tracking data are expensive to collect, requiring specialized hardware and controlled laboratory conditions, and difficult to share because of pr...
arXiv:2507. 15833v3 Announce Type: replace-cross Abstract: Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation, dramatically reducing visual processing.
The paper introduces SalTempto, a new video saliency benchmark featuring 224 highly dynamic clips from HACS‑Segments, each with event context and gaze data from up to 16 subjects. It shows that static baselines perform poorly on SalTempto compared to LEDOV, while fine‑tuned temporal models achieve significant gains, yet still leave a large portion of explainable gaze information unaccounted for. The dataset highlights the need for better temporal modeling in video saliency research.