More Like this

1. Learning Integrated Holism-Landmark Representations for Long-Term Loop Closure Detection

   Fei Han, Hua Wang (January 2018, The Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI 2018))

   Loop closure detection is a critical component of large-scale simultaneous localization and mapping (SLAM) in loopy environments. This capability is challenging to achieve in long-term SLAM, when the environment appearance exhibits significant long-term variations across various time of the day, months, and even seasons. In this paper, we introduce a novel formulation to learn an integrated long-term representation based upon both holistic and landmark information, which integrates two previous insights under a unified framework: (1) holistic representations outperform keypoint-based representations, and (2) landmarks as an intermediate representation provide informative cues to detect challenging locations. Our new approach learns the representation by projecting input visual data into a low-dimensional space, which preserves both the global consistency (to minimize representation error) and the local consistency (to preserve landmarks’ pairwise relationship) of the input data. To solve the formulated optimization problem, a new algorithm is developed with theoretically guaranteed convergence. Extensive experiments have been conducted using two large-scale public benchmark data sets, in which the promising performances have demonstrated the effectiveness of the proposed approach. 

   more » « less
2. A Fast and Robust Place Recognition Approach for Stereo Visual Odometry Using LiDAR Descriptors

   https://doi.org/10.1109/IROS45743.2020.9341733  

   Mo, Jiawei; Sattar, Junaed (October 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS))

   null (Ed.)

   Place recognition is a core component of Simultaneous Localization and Mapping (SLAM) algorithms. Particularly in visual SLAM systems, previously-visited places are recognized by measuring the appearance similarity between images representing these locations. However, such approaches are sensitive to visual appearance change and also can be computationally expensive. In this paper, we propose an alternative approach adapting LiDAR descriptors for 3D points obtained from stereo-visual odometry for place recognition. 3D points are potentially more reliable than 2D visual cues (e.g., 2D features) against environmental changes (e.g., variable illumination) and this may benefit visual SLAM systems in long-term deployment scenarios. Stereo-visual odometry generates 3D points with an absolute scale, which enables us to use LiDAR descriptors for place recognition with high computational efficiency. Through extensive evaluations on standard benchmark datasets, we demonstrate the accuracy, efficiency, and robustness of using 3D points for place recognition over 2D methods. 

   more » « less
3. Dynamic Motion Representation for Human Action Recognition

   https://doi.org/10.1109/WACV45572.2020.9093500  

   Asghari-Esfeden, Sadjad; Sznaier, Mario; Camps, Octavia (March 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV))

   Despite the advances in Human Activity Recognition, the ability to exploit the dynamics of human body motion in videos has yet to be achieved. In numerous recent works, re- searchers have used appearance and motion as independent inputs to infer the action that is taking place in a specific video. In this paper, we highlight that while using a novel representation of human body motion, we can benefit from appearance and motion simultaneously. As a result, bet- ter performance of action recognition can be achieved. We start with a pose estimator to extract the location and heat- map of body joints in each frame. We use a dynamic encoder to generate a fixed size representation from these body joint heat-maps. Our experimental results show that training a convolutional neural network with the dynamic motion representation outperforms state-of-the-art action recognition models. By modeling distinguishable activities as distinct dynamical systems and with the help of two stream net- works, we obtain the best performance on HMDB, JHMDB, UCF-101, and AVA datasets. 

   more » « less
4. Contemplating Visual Emotions: Understanding and Overcoming Dataset Bias

   Panda, R.; Zhang, J.; Li, H.; Lee, J.; Lu, X.; Roy-Chowdhury, R. (September 2018, European Conf. on Computer Vision)

   While machine learning approaches to visual emotion recognition oer great promise, current methods consider training and testing models on small scale datasets covering limited visual emotion concepts. Our analysis identi es an important but long overlooked issue of existing visual emotion benchmarks in the form of dataset biases. We design a series of tests to show and measure how such dataset biases obstruct learning a generalizable emotion recognition model. Based on our analysis, we propose a webly supervised approach by leveraging a large quantity of stock image data. Our approach uses a simple yet eective curriculum guided training strategy for learning discriminative emotion features. We discover that the models learned using our large scale stock image dataset exhibit signi cantly better generalization ability than the existing datasets without the manual collection of even a single label. Moreover, visual representation learned using our approach holds a lot of promise across a variety of tasks on dierent image and video datasets. 

   more » « less
5. Have Fun Storming the Castle(s)!

   https://doi.org/10.1109/WACV48630.2021.00375  

   Anderson, Connor; Teuscher, Adam; Anderson, Elizabeth; Larsen, Alysia; Shirley, Josh; Farrell, Ryan (January 2021, IEEE Winter Conference on Applications of Computer Vision (WACV))

   In recent years, large-scale datasets, each typically tailored to a particular problem, have become a critical factor towards fueling rapid progress in the field of computer vision. This paper describes a valuable new dataset that should accelerate research efforts on problems such as fine-grained classification, instance recognition and retrieval, and geolocalization. The dataset, comprised of more than 2400 individual castles, palaces and fortresses from more than 90 countries, contains more than 770K images in total. This paper details the dataset's construction process, the characteristics including annotations such as location (geotagged latlong and country label), construction date, Google Maps link and estimated per-class and per-image difficulty. An experimental section provides baseline experiments for important vision tasks including classification, instance retrieval and geolocalization (estimating global location from an image's visual appearance). The dataset is publicly available at vision.cs.byu.edu/castles. 

   more » « less