5 accepted papers
Unsupervised text encoding models have recently fueled substantial progress in NLP. The key idea is to use neural networks to convert words in texts to vector space representations (embeddings) based on word positions in a sentence and their contexts, which are suitable for end-to-end training of do…
The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values. Then the majority of computation costs focus on the integer mat…
Traditional Exemplar-SVMs (ESVM) require millions of negative samples to establish a linear exemplar detector. However, Exemplar Linear Discriminant Analysis (ELDA) can achieve similar performance while avoid negative samples mining. To construct a strong object classifier, Multiple Instance Learnin…
In this paper, we propose a robust obstacle detection approach by leveraging Weighted Hough Transform (WHT) in combination with temporal information correlation from the stereo video sequences. First, to model the road surface or obstacles in the video, rather than using simple threshold from binari…
Interactive mobile vision applications, such as Mobile Landmark Recognition (MLR), have recently attracted ever increasing research attention due to the exponential growth of mobile devices. However, the recognition accuracy retains as a bottleneck hesitating the proliferation of such applications.…