Deep Radial Embedding for Visual Sequence Learning
Connectionist Temporal Classification (CTC) is a popular objective function in sequence recognition, which provides supervision for unsegmented sequence data through aligning sequence and its corresponding labeling iteratively. The blank class of CTC plays a crucial role in the alignment process and is often considered responsible for the peaky behavior of CTC. In this study, we propose an objective function named RadialCTC that constrains sequence features on a hypersphere while retaining the iterative alignment mechanism of CTC. The learned features of each non-blank class are distributed on a radial arc from the center of the blank class, which provides a clear geometric interpretation and makes the alignment process more efficient. Besides, RadialCTC can control the peaky behavior by simply modifying the logit of the blank class. Experimental results of recognition and localization demonstrate the effectiveness of RadialCTC on two sequence recognition applications.
Code (0)
등록된 구현이 없습니다.
Tasks
ARCSign Language RecognitionSimilar Papers 제목 키워드 기반
3D Velocity from 3D Doppler Radial Velocity
We present local least squares and regularization frameworks for computing 3D velocity (3D optical flow) from 3D radial velocity measured by a Doppler radar. We demonstrate the performance of our algorithms quantitativ…
Optical Flow Estimation3D-RadViz: Three Dimensional Radial Visualization for Large-Scale Data Visualization
This paper presents 3D-RadViz, a visualization method for high dimensional data using a three dimensional radial visualization technique. The proposed technique extends the capabilities of the classical two dimensional r…
Data VisualizationNeurally-plausible radial basis kernels using distributed Fourier embeddings
Coherent, continuous spatial representations are critical for synthesizing physical and perceptual phenomena into a single representational space. Radial basis kernels provide a path forward for this type of distributed …
Nearest Neighbour Radial Basis Function Solvers for Deep Neural Networks
We present a radial basis function solver for convolutional neural networks that can be directly applied to both distance metric learning and classification problems. Our method treats all training features from a deep n…
ClassificationGeneral ClassificationMetric LearningA Deep Learning-Based Target Radial Length Estimation Method through HRRP Sequence
This paper introduces an innovative deep learning-based method for end-to-end target radial length estimation from HRRP (High Resolution Range Profile) sequences. Firstly, the HRRP sequences are normalized and transforme…