Gregory Zelinsky

Zhibo Yang, Sounak Mondal, Seoyoung Ahn et al.

Most models of visual attention aim at predicting either top-down or bottom-up control, as studied using different visual search and free-viewing tasks. In this paper we propose the Human Attention Transformer (HAT), a single model that predicts both forms of attention control. HAT uses a novel transformer-based architecture and a simplified foveated retina that collectively create a spatio-temporal awareness akin to the dynamic visual working memory of humans. HAT not only establishes a new state-of-the-art in predicting the scanpath of fixations made during target-present and target-absent visual search and ``taskless'' free viewing, but also makes human gaze behavior interpretable. Unlike previous methods that rely on a coarse grid of fixation cells and experience information loss due to fixation discretization, HAT features a sequential dense prediction architecture and outputs a dense heatmap for each fixation, thus avoiding discretizing fixations. HAT sets a new standard in computational attention, which emphasizes effectiveness, generality, and interpretability. HAT's demonstrated scope and applicability will likely inspire the development of new attention models that can better predict human behavior in various attention-demanding scenarios. Code is available at https://github.com/cvlab-stonybrook/HAT.

Sounak Mondal, Zhibo Yang, Seoyoung Ahn et al.

Predicting human gaze is important in Human-Computer Interaction (HCI). However, to practically serve HCI applications, gaze prediction models must be scalable, fast, and accurate in their spatial and temporal gaze predictions. Recent scanpath prediction models focus on goal-directed attention (search). Such models are limited in their application due to a common approach relying on trained target detectors for all possible objects, and the availability of human gaze data for their training (both not scalable). In response, we pose a new task called ZeroGaze, a new variant of zero-shot learning where gaze is predicted for never-before-searched objects, and we develop a novel model, Gazeformer, to solve the ZeroGaze problem. In contrast to existing methods using object detector modules, Gazeformer encodes the target using a natural language model, thus leveraging semantic similarities in scanpath prediction. We use a transformer-based encoder-decoder architecture because transformers are particularly useful for generating contextual representations. Gazeformer surpasses other models by a large margin on the ZeroGaze setting. It also outperforms existing target-detection models on standard gaze prediction for both target-present and target-absent search tasks. In addition to its improved performance, Gazeformer is more than five times faster than the state-of-the-art target-present visual search model.

Zhibo Yang, Sounak Mondal, Seoyoung Ahn et al.

The prediction of human gaze behavior is important for building human-computer interactive systems that can anticipate a user's attention. Computer vision models have been developed to predict the fixations made by people as they search for target objects. But what about when the image has no target? Equally important is to know how people search when they cannot find a target, and when they would stop searching. In this paper, we propose the first data-driven computational model that addresses the search-termination problem and predicts the scanpath of search fixations made by people searching for targets that do not appear in images. We model visual search as an imitation learning problem and represent the internal knowledge that the viewer acquires through fixations using a novel state representation that we call Foveated Feature Maps (FFMs). FFMs integrate a simulated foveated retina into a pretrained ConvNet that produces an in-network feature pyramid, all with minimal computational overhead. Our method integrates FFMs as the state representation in inverse reinforcement learning. Experimentally, we improve the state of the art in predicting human target-absent search behavior on the COCO-Search18 dataset

Hossein Adeli, Seoyoung Ahn, Nikolaus Kriegeskorte et al.

The spreading of attention has been proposed as a mechanism for how humans group features to segment objects. However, such a mechanism has not yet been implemented and tested in naturalistic images. Here, we leverage the feature maps from self-supervised vision Transformers and propose a model of human object-based attention spreading and segmentation. Attention spreads within an object through the feature affinity signal between different patches of the image. We also collected behavioral data on people grouping objects in natural images by judging whether two dots are on the same object or on two different objects. We found that our models of affinity spread that were built on feature maps from the self-supervised Transformers showed significant improvement over baseline and CNN based models on predicting reaction time patterns of humans, despite not being trained on the task or with any other object labels. Our work provides new benchmarks for evaluating models of visual representation learning including Transformers.

Sounak Mondal, Seoyoung Ahn, Zhibo Yang et al.

For computer systems to effectively interact with humans using spoken language, they need to understand how the words being generated affect the users' moment-by-moment attention. Our study focuses on the incremental prediction of attention as a person is seeing an image and hearing a referring expression defining the object in the scene that should be fixated by gaze. To predict the gaze scanpaths in this incremental object referral task, we developed the Attention in Referral Transformer model or ART, which predicts the human fixations spurred by each word in a referring expression. ART uses a multimodal transformer encoder to jointly learn gaze behavior and its underlying grounding tasks, and an autoregressive transformer decoder to predict, for each word, a variable number of fixations based on fixation history. To train ART, we created RefCOCO-Gaze, a large-scale dataset of 19,738 human gaze scanpaths, corresponding to 2,094 unique image-expression pairs, from 220 participants performing our referral task. In our quantitative and qualitative analyses, ART not only outperforms existing methods in scanpath prediction, but also appears to capture several human attention patterns, such as waiting, scanning, and verification.

Hossein Adeli, Seoyoung Ahn, Andrew Luo et al.

Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties. However, their alignment with human object perception remains poorly understood. Here, we introduce a behavioral benchmark in which participants make same/different object judgments for dot pairs on naturalistic scenes, scaling up a classical psychophysics paradigm to over 1000 trials. We test a diverse set of vision models using a simple readout from their representations to predict subjects' reaction times. We observe a steady improvement across model generations, with both architecture and training objective contributing to alignment, and transformer-based models trained with the DINO self-supervised objective showing the strongest performance. To investigate the source of this improvement, we propose a novel metric to quantify the object-centric component of representations by measuring patch similarity within and between objects. Across models, stronger object-centric structure predicts human segmentation behavior more accurately. We further show that matching the Gram matrix of supervised transformer models, capturing similarity structure across image patches, with that of a self-supervised model through distillation improves their alignment with human behavior, converging with the prior finding that Gram anchoring improves DINOv3's feature quality. Together, these results demonstrate that self-supervised vision models capture object structure in a behaviorally human-like manner, and that Gram matrix structure plays a role in driving perceptual alignment.

Ruoyu Xue, Hieu Le, Jingyi Xu et al.

People can view the same image differently: they focus on different regions, objects, and details in varying orders and describe them in distinct linguistic styles. This leads to substantial variability in image descriptions. However, existing models for personalized image description focus on linguistic style alone, with no prior work leveraging individual viewing patterns. We address this gap by explicitly modeling personalized viewing behavior as a core factor in description generation. Our method, DEPER (DEscription-PERception persona encoder), learns a subject embedding that captures both linguistic style and viewing behavior, guided by an auxiliary attention-prediction task. A lightweight adapter aligns these embeddings with a frozen vision-language model, enabling few-shot personalization without retraining. Across four datasets spanning diverse viewing tasks and both short and detailed descriptions, DEPER achieves a 24% average improvement, showing that modeling personalized attention produces more human-aligned and high-quality descriptions. We posit that understanding how people see helps predict what they say; modeling human diversity in perception can improve both performance and human alignment in multimodal systems.

Ruoyu Xue, Jingyi Xu, Sounak Mondal et al.

A personalized model for scanpath prediction provides insights into the visual preferences and attention patterns of individual subjects. However, existing methods for training scanpath prediction models are data-intensive and cannot be effectively personalized to new individuals with only a few available examples. In this paper, we propose few-shot personalized scanpath prediction task (FS-PSP) and a novel method to address it, which aims to predict scanpaths for an unseen subject using minimal support data of that subject's scanpath behavior. The key to our method's adaptability is the Subject-Embedding Network (SE-Net), specifically designed to capture unique, individualized representations for each subject's scanpaths. SE-Net generates subject embeddings that effectively distinguish between subjects while minimizing variability among scanpaths from the same individual. The personalized scanpath prediction model is then conditioned on these subject embeddings to produce accurate, personalized results. Experiments on multiple eye-tracking datasets demonstrate that our method excels in FS-PSP settings and does not require any fine-tuning steps at test time. Code is available at: https://github.com/cvlab-stonybrook/few-shot-scanpath

Peter Zeng, Weiling Li, Amie Paige et al.

For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical. But this ability to collaborate remains limited by a critical deficit: an inability to model common ground. Here, we present a referential communication experiment with a factorial design involving director-matcher pairs (human-human, human-AI, AI-human, and AI-AI) that interact with multiple turns in repeated rounds to match pictures of objects not associated with any obvious lexicalized labels. We release the online pipeline for data collection, the tools and analyses for accuracy, efficiency, and lexical overlap, and a corpus of 356 dialogues (89 pairs over 4 rounds each) that unmasks LVLMs' limitations in interactively resolving referring expressions, a crucial skill that underlies human language use.

Souradeep Chakraborty, Ruoyu Xue, Rajarsi Gupta et al.

The ability to predict the attention of expert pathologists could lead to decision support systems for better pathology training. We developed methods to predict the spatio-temporal (where and when) movements of pathologists' attention as they grade whole slide images (WSIs) of prostate cancer. We characterize a pathologist's attention trajectory by their x, y, and m (magnification) movements of a viewport as they navigate WSIs using a digital microscope. This information was obtained from 43 pathologists across 123 WSIs, and we consider the task of predicting the pathologist attention scanpaths constructed from the viewport centers. We introduce a fixation extraction algorithm that simplifies an attention trajectory by extracting fixations in the pathologist's viewing while preserving semantic information, and we use these pre-processed data to train and test a two-stage model to predict the dynamic (scanpath) allocation of attention during WSI reading via intermediate attention heatmap prediction. In the first stage, a transformer-based sub-network predicts the attention heatmaps (static attention) across different magnifications. In the second stage, we predict the attention scanpath by sequentially modeling the next fixation points in an autoregressive manner using a transformer-based approach, starting at the WSI center and leveraging multi-magnification feature representations from the first stage. Experimental results show that our scanpath prediction model outperforms chance and baseline models. Tools developed from this model could assist pathology trainees in learning to allocate their attention during WSI reading like an expert.

Hossein Adeli, Seoyoung Ahn, Gregory Zelinsky

The visual system processes a scene using a sequence of selective glimpses, each driven by spatial and object-based attention. These glimpses reflect what is relevant to the ongoing task and are selected through recurrent processing and recognition of the objects in the scene. In contrast, most models treat attention selection and recognition as separate stages in a feedforward process. Here we show that using capsule networks to create an object-centric hidden representation in an encoder-decoder model with iterative glimpse attention yields effective integration of attention and recognition. We evaluate our model on three multi-object recognition tasks; highly overlapping digits, digits among distracting clutter and house numbers, and show that it learns to effectively move its glimpse window, recognize and reconstruct the objects, all with only the classification as supervision. Our work takes a step toward a general architecture for how to integrate recurrent object-centric representation into the planning of attentional glimpses.

Raji Annadi, Yupei Chen, Viresh Ranjan et al.

In this paper, we describe our study on how humans allocate their attention during visual crowd counting. Using an eye tracker, we collect gaze behavior of human participants who are tasked with counting the number of people in crowd images. Analyzing the collected gaze behavior of ten human participants on thirty crowd images, we observe some common approaches for visual counting. For an image of a small crowd, the approach is to enumerate over all people or groups of people in the crowd, and this explains the high level of similarity between the fixation density maps of different human participants. For an image of a large crowd, our participants tend to focus on one section of the image, count the number of people in that section, and then extrapolate to the other sections. In terms of count accuracy, our human participants are not as good at the counting task, compared to the performance of the current state-of-the-art computer algorithms. Interestingly, there is a tendency to under count the number of people in all crowd images. Gaze behavior data and images can be downloaded from https://www3.cs.stonybrook.edu/~minhhoai/projects/crowd_counting_gaze/.

Zhibo Yang, Lihan Huang, Yupei Chen et al.

Being able to predict human gaze behavior has obvious importance for behavioral vision and for computer vision applications. Most models have mainly focused on predicting free-viewing behavior using saliency maps, but these predictions do not generalize to goal-directed behavior, such as when a person searches for a visual target object. We propose the first inverse reinforcement learning (IRL) model to learn the internal reward function and policy used by humans during visual search. The viewer's internal belief states were modeled as dynamic contextual belief maps of object locations. These maps were learned by IRL and then used to predict behavioral scanpaths for multiple target categories. To train and evaluate our IRL model we created COCO-Search18, which is now the largest dataset of high-quality search fixations in existence. COCO-Search18 has 10 participants searching for each of 18 target-object categories in 6202 images, making about 300,000 goal-directed fixations. When trained and evaluated on COCO-Search18, the IRL model outperformed baseline models in predicting search fixation scanpaths, both in terms of similarity to human search behavior and search efficiency. Finally, reward maps recovered by the IRL model reveal distinctive target-dependent patterns of object prioritization, which we interpret as a learned object context.

Hossein Adeli, Gregory Zelinsky

Recent machine learning models have shown that including attention as a component results in improved model accuracy and interpretability, despite the concept of attention in these approaches only loosely approximating the brain's attention mechanism. Here we extend this work by building a more brain-inspired deep network model of the primate ATTention Network (ATTNet) that learns to shift its attention so as to maximize the reward. Using deep reinforcement learning, ATTNet learned to shift its attention to the visual features of a target category in the context of a search task. ATTNet's dorsal layers also learned to prioritize these shifts of attention so as to maximize success of the ventral pathway classification and receive greater reward. Model behavior was tested against the fixations made by subjects searching images for the same cued category. Both subjects and ATTNet showed evidence for attention being preferentially directed to target goals, behaviorally measured as oculomotor guidance to targets. More fundamentally, ATTNet learned to shift its attention to target like objects and spatially route its visual inputs to accomplish the task. This work makes a step toward a better understanding of the role of attention in the brain and other computational systems.

Hieu Le, Chen-Ping Yu, Gregory Zelinsky et al.

Co-localization is the problem of localizing objects of the same class using only the set of images that contain them. This is a challenging task because the object detector must be built without negative examples that can lead to more informative supervision signals. The main idea of our method is to cluster the feature space of a generically pre-trained CNN, to find a set of CNN features that are consistently and highly activated for an object category, which we call category-consistent CNN features. Then, we propagate their combined activation map using superpixel geodesic distances for co-localization. In our first set of experiments, we show that the proposed method achieves state-of-the-art performance on three related benchmarks: PASCAL 2007, PASCAL-2012, and the Object Discovery dataset. We also show that our method is able to detect and localize truly unseen categories, on six held-out ImageNet categories with accuracy that is significantly higher than previous state-of-the-art. Our intuitive approach achieves this success without any region proposals or object detectors and can be based on a CNN that was pre-trained purely on image classification tasks without further fine-tuning.