skip to main content

Title: Unsupervised Gaze Prediction in Egocentric Videos by Energy-based Surprise Modeling
Egocentric perception has grown rapidly with the advent of immersive computing devices. Human gaze prediction is an important problem in analyzing egocentric videos and has primarily been tackled through either saliency-based modeling or highly supervised learning. We quantitatively analyze the generalization capabilities of supervised, deep learning models on the egocentric gaze prediction task on unseen, out-of-domain data. We find that their performance is highly dependent on the training data and is restricted to the domains specified in the training annotations. In this work, we tackle the problem of jointly predicting human gaze points and temporal segmentation of egocentric videos without using any training data. We introduce an unsupervised computational model that draws inspiration from cognitive psychology models of event perception. We use Grenander's pattern theory formalism to represent spatial-temporal features and model surprise as a mechanism to predict gaze fixation points. Extensive evaluation on two publicly available datasets - GTEA and GTEA+ datasets-shows that the proposed model can significantly outperform all unsupervised baselines and some supervised gaze prediction baselines. Finally, we show that the model can also temporally segment egocentric videos with a performance comparable to more complex, fully supervised deep learning baselines.
Authors:
;
Award ID(s):
1955230
Publication Date:
NSF-PAR ID:
10278137
Journal Name:
International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Sponsoring Org:
National Science Foundation
More Like this
  1. Vedaldi, A. ; Bischof, H. ; Brox, T. ; Frahm, JM. (Ed.)
    The problem of action localization involves locating the action in the video, both over time and spatially in the image. The current dominant approaches use supervised learning to solve this problem. They require large amounts of annotated training data, in the form of frame-level bounding box annotations around the region of interest. In this paper, we present a new approach based on continual learning that uses feature-level predictions for self-supervision. It does not require any training annotations in terms of frame-level bounding boxes. The approach is inspired by cognitive models of visual event perception that propose a prediction-based approach tomore »event understanding. We use a stack of LSTMs coupled with a CNN encoder, along with novel attention mechanisms, to model the events in the video and use this model to predict high-level features for the future frames. The prediction errors are used to learn the parameters of the models continuously. This self-supervised framework is not complicated as other approaches but is very effective in learning robust visual representations for both labeling and localization. It should be noted that the approach outputs in a streaming fashion, requiring only a single pass through the video, making it amenable for real-time processing. We demonstrate this on three datasets - UCF Sports, JHMDB, and THUMOS’13 and show that the proposed approach outperforms weakly-supervised and unsupervised baselines and obtains competitive performance compared to fully supervised baselines. Finally, we show that the proposed framework can generalize to egocentric videos and achieve state-of-the-art results on the unsupervised gaze prediction task.« less
  2. Event perception tasks such as recognizing and localizing actions in streaming videos are essential for scaling to real-world application contexts. We tackle the problem of learning actor-centered representations through the notion of continual hierarchical predictive learning to localize actions in streaming videos without the need for training labels and outlines for the objects in the video. We propose a framework driven by the notion of hierarchical predictive learning to construct actor-centered features by attention-based contextualization. The key idea is that predictable features or objects do not attract attention and hence do not contribute to the action of interest. Experiments onmore »three benchmark datasets show that the approach can learn robust representations for localizing actions using only one epoch of training, i.e., a single pass through the streaming video. We show that the proposed approach outperforms unsupervised and weakly supervised baselines while offering competitive performance to fully supervised approaches. Additionally, we extend the model to multi-actor settings to recognize group activities while localizing the multiple, plausible actors. We also show that it generalizes to out-of-domain data with limited performance degradation.« less
  3. Relevance to proposal: This project evaluates the generalizability of real and synthetic training datasets which can be used to train model-free techniques for multi-agent applications. We evaluate different methods of generating training corpora and machine learning techniques including Behavior Cloning and Generative Adversarial Imitation Learning. Our results indicate that the utility-guided selection of representative scenarios to generate synthetic data can have significant improvements on model performance. Paper abstract: Crowd simulation, the study of the movement of multiple agents in complex environments, presents a unique application domain for machine learning. One challenge in crowd simulation is to imitate the movement ofmore »expert agents in highly dense crowds. An imitation model could substitute an expert agent if the model behaves as good as the expert. This will bring many exciting applications. However, we believe no prior studies have considered the critical question of how training data and training methods affect imitators when these models are applied to novel scenarios. In this work, a general imitation model is represented by applying either the Behavior Cloning (BC) training method or a more sophisticated Generative Adversarial Imitation Learning (GAIL) method, on three typical types of data domains: standard benchmarks for evaluating crowd models, random sampling of state-action pairs, and egocentric scenarios that capture local interactions. Simulated results suggest that (i) simpler training methods are overall better than more complex training methods, (ii) training samples with diverse agent-agent and agent-obstacle interactions are beneficial for reducing collisions when the trained models are applied to new scenarios. We additionally evaluated our models in their ability to imitate real world crowd trajectories observed from surveillance videos. Our findings indicate that models trained on representative scenarios generalize to new, unseen situations observed in real human crowds.« less
  4. This work proposes an Adaptive Fuzzy Prediction (AFP) method for the attenuation time series in Commercial Microwave links (CMLs). Time-series forecasting models regularly rely on the assumption that the entire data set follows the same Data Generating Process (DGP). However, the signals in wireless microwave links are severely affected by the varying weather conditions in the channel. Consequently, the attenuation time series might change its characteristics significantly at different periods. We suggest an adaptive framework to better employ the training data by grouping sequences with related temporal patterns to consider the non-stationary nature of the signals. The focus in thismore »work is two-folded. The first is to explore the integration of static data of the CMLs as exogenous variables for the attenuation time series models to adopt diverse link characteristics. This extension allows to include various attenuation datasets obtained from additional CMLs in the training process and dramatically increasing available training data. The second is to develop an adaptive framework for short-term attenuation forecasting by employing an unsupervised fuzzy clustering procedure and supervised learning models. We empirically analyzed our framework for model and data-driven approaches with Recurrent Neural Network (RNN) and Autoregressive Integrated Moving Average (ARIMA) variations. We evaluate the proposed extensions on real-world measurements collected from 4G backhaul networks, considering dataset availability and the accuracy for 60 seconds prediction. We show that our framework can significantly improve conventional models’ accuracy and that incorporating data from various CMLs is essential to the AFP framework. The proposed methods have been shown to enhance the forecasting model’s performance by 30 − 40%, depending on the specific model and the data availability.« less
  5. Urban traffic status (e.g., traffic speed and volume) is highly dynamic in nature, namely, varying across space and evolving over time. Thus, predicting such traffic dynamics is of great importance to urban development and transportation management. However, it is very challenging to solve this problem due to spatial-temporal dependencies and traffic uncertainties. In this article, we solve the traffic dynamics prediction problem from Bayesian meta-learning perspective and propose a novel continuous spatial-temporal meta-learner (cST-ML), which is trained on a distribution of traffic prediction tasks segmented by historical traffic data with the goal of learning a strategy that can be quicklymore »adapted to related but unseen traffic prediction tasks. cST-ML tackles the traffic dynamics prediction challenges by advancing the Bayesian black-box meta-learning framework through the following new points: (1) cST-ML captures the dynamics of traffic prediction tasks using variational inference, and to better capture the temporal uncertainties within tasks, cST-ML performs as a rolling window within each task; (2) cST-ML has novel designs in architecture, where CNN and LSTM are embedded to capture the spatial-temporal dependencies between traffic status and traffic-related features; (3) novel training and testing algorithms for cST-ML are designed. We also conduct experiments on two real-world traffic datasets (taxi inflow and traffic speed) to evaluate our proposed cST-ML. The experimental results verify that cST-ML can significantly improve the urban traffic prediction performance and outperform all baseline models especially when obvious traffic dynamics and temporal uncertainties are presented.« less