Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHigh Five: Improving Gesture Recognition by Embracing Uncertainty
51
0
0.0
(
0
)
Added by
Diman Zad Tootaghaj
Publication date
2017
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Sensors on mobile devices---accelerometers, gyroscopes, pressure meters, and GPS---invite new applications in gesture recognition, gaming, and fitness tracking. However, programming them remains challenging because human gestures captured by sensors are noisy. This paper illustrates that noisy gestures degrade training and classification accuracy for gesture recognition in state-of-the-art deterministic Hidden Markov Models (HMM). We introduce a new statistical quantization approach that mitigates these problems by (1) during training, producing gesture-specific codebooks, HMMs, and error models for gesture sequences; and (2) during classification, exploiting the error model to explore multiple feasible HMM state sequences. We implement classification in Uncertain<t>, a probabilistic programming system that encapsulates HMMs and error models and then automates sampling and inference in the runtime. Uncertain<T> developers directly express a choice of application-specific trade-off between recall and precision at gesture recognition time, rather than at training time. We demonstrate benefits in configurability, precision, recall, and recognition on two data sets with 25 gestures from 28 people and 4200 total gestures. Incorporating gesture error more accurately in modeling improves the average recognition rate of 20 gestures from 34% in prior work to 62%. Incorporating the error model during classification further improves the average gesture recognition rate to 71%. As far as we are aware, no prior work shows how to generate an HMM error model during training and use it to improve classification rates.
rate research
Read More
Temporal grounding aims to localize temporal boundaries within untrimmed videos by language queries, but it faces the challenge of two types of inevitable human uncertainties: query uncertainty and label uncertainty. The two uncertainties stem from human subjectivity, leading to limited generalization ability of temporal grounding. In this work, we propose a novel DeNet (Decoupling and De-bias) to embrace human uncertainty: Decoupling - We explicitly disentangle each query into a relation feature and a modified feature. The relation feature, which is mainly based on skeleton-like words (including nouns and verbs), aims to extract basic and consistent information in the presence of query uncertainty. Meanwhile, modified feature assigned with style-like words (including adjectives, adverbs, etc) represents the subjective information, and thus brings personalized predictions; De-bias - We propose a de-bias mechanism to generate diverse predictions, aim to alleviate the bias caused by single-style annotations in the presence of label uncertainty. Moreover, we put forward new multi-label metrics to diversify the performance evaluation. Extensive experiments show that our approach is more effective and robust than state-of-the-arts on Charades-STA and ActivityNet Captions datasets.
Visual place recognition (VPR) is the problem of recognising a previously visited location using visual information. Many attempts to improve the performance of VPR methods have been made in the literature. One approach that has received attention recently is the multi-process fusion where different VPR methods run in parallel and their outputs are combined in an effort to achieve better performance. The multi-process fusion, however, does not have a well-defined criterion for selecting and combining different VPR methods from a wide range of available options. To the best of our knowledge, this paper investigates the complementarity of state-of-the-art VPR methods systematically for the first time and identifies those combinations which can result in better performance. The paper presents a well-defined framework which acts as a sanity check to find the complementarity between two techniques by utilising a McNemars test-like approach. The framework allows estimation of upper and lower complementarity bounds for the VPR techniques to be combined, along with an estimate of maximum VPR performance that may be achieved. Based on this framework, results are presented for eight state-of-the-art VPR methods on ten widely-used VPR datasets showing the potential of different combinations of techniques for achieving better performance.
We propose a novel appearance-based gesture recognition algorithm using compressed domain signal processing techniques. Gesture features are extracted directly from the compressed measurements, which are the block averages and the coded linear combinations of the image sensors pixel values. We also improve both the computational efficiency and the memory requirement of the previous DTW-based K-NN gesture classifiers. Both simulation testing and hardware implementation strongly support the proposed algorithm.
Static gesture recognition is an effective non-verbal communication channel between a user and their devices; however many modern methods are sensitive to the relative pose of the users hands with respect to the capture device, as parts of the gesture can become occluded. We present two methodologies for gesture recognition via synchronized recording from two depth cameras to alleviate this occlusion problem. One is a more classic approach using iterative closest point registration to accurately fuse point clouds and a single PointNet architecture for classification, and the other is a dual Point-Net architecture for classification without registration. On a manually collected data-set of 20,100 point clouds we show a 39.2% reduction in misclassification for the fused point cloud method, and 53.4% for the dual PointNet, when compared to a standard single camera pipeline.
We explore object detection with two attributes: color and material. The task aims to simultaneously detect objects and infer their color and material. A straight-forward approach is to add attribute heads at the very end of a usual object detection pipeline. However, we observe that the two goals are in conflict: Object detection should be attribute-independent and attributes be largely object-independent. Features computed by a standard detection network entangle the category and attribute features; we disentangle them by the use of a two-stream model where the category and attribute features are computed independently but the classification heads share Regions of Interest (RoIs). Compared with a traditional single-stream model, our model shows significant improvements over VG-20, a subset of Visual Genome, on both supervised and attribute transfer tasks.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
