1 code implementation • 14 Jun 2023 • Meng Shen, Yizheng Huang, Jianxiong Yin, Heqing Zou, Deepu Rajan, Simon See
Our studies demonstrate that the proposed method achieves more balanced multimodal learning by avoiding greedy sample selection from the dominant modality.
1 code implementation • 16 May 2023 • Heqing Zou, Meng Shen, Chen Chen, Yuchen Hu, Deepu Rajan, Eng Siong Chng
Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks.
1 code implementation • 29 Mar 2022 • Heqing Zou, Yuke Si, Chen Chen, Deepu Rajan, Eng Siong Chng
In this paper, we propose an end-to-end speech emotion recognition system using multi-level acoustic information with a newly designed co-attention module.
no code implementations • 12 Sep 2018 • Dilip K. Prasad, Huixu Dong, Deepu Rajan, Chai Quek
However, the conventional assessment metrics suitable for usual object detection are deficient in the maritime setting.
no code implementations • 15 Apr 2017 • Raj Kumar Gupta, Alex Yong-Sang Chia, Deepu Rajan, Huang Zhiyong
In this paper, we present a color transfer algorithm to colorize a broad range of gray images without any user intervention.
no code implementations • 9 Feb 2017 • Jubin Johnson, Hisham Cholakkal, Deepu Rajan
Sampling-based alpha matting methods have traditionally followed the compositing equation to estimate the alpha value at a pixel from a pair of foreground (F) and background (B) samples.
no code implementations • 16 Nov 2016 • Hisham Cholakkal, Jubin Johnson, Deepu Rajan
First, the probabilistic contribution of each image region to the confidence of a CNN-based image classifier is computed through a backtracking strategy to produce top-down saliency.
no code implementations • CVPR 2016 • Hisham Cholakkal, Jubin Johnson, Deepu Rajan
We propose a weakly supervised top-down saliency framework using only binary labels that indicate the presence/absence of an object in an image.
no code implementations • 22 Apr 2016 • Hisham Cholakkal, Jubin Johnson, Deepu Rajan
Although the role of the classifier is to support salient object detection, we evaluate its performance in image classification and also illustrate the utility of thresholded saliency maps for image segmentation.
no code implementations • 11 Apr 2016 • Jubin Johnson, Ehsan Shahrian Varnousfaderani, Hisham Cholakkal, Deepu Rajan
In this paper, the matting problem is reinterpreted as a sparse coding of pixel features, wherein the sum of the codes gives the estimate of the alpha matte from a set of unpaired F and B samples.
no code implementations • CVPR 2013 • Ehsan Shahrian, Deepu Rajan, Brian Price, Scott Cohen
The first is that the range in which the foreground and background are sampled is often limited to such an extent that the true foreground and background colors are not present.