Search Publication
] . Region-based depth map coding using a 3D scene representation. In IEEE International Conference on Acoustics, Speech and Signal Processing. Brisbane, Australia; 2015. 
(1.35 MB)
(1.35 MB). Region-based Particle Filter. . 2015.
. Region-oriented Convolutional Networks for Object Retrieval. . 2015. (8.02 MB)
(8.02 MB). Saliency Maps on Image Hierarchies. Signal Processing: Image Communication. Special Issue on Recent Advances in Saliency Models, Applications and Evaluations. 2015;38:84-99.
. Semantic and Diverse Summarization of Egocentric Photo Events. . 2015. (5.34 MB)
(5.34 MB). Study of Binary Partition Tree Pruning Techniques for Polarimetric SAR images. In International Symposium on Mathematical Morphology, ISMM 2015. Reykjavik, Iceland: Springer; 2015. (2.52 MB)
(2.52 MB). Study of Normalization and Aggregation Approaches for Consensus Network Estimation. In 2015 IEEE Symposium Series on Computational Intelligence: IEEE Symposium on Artificial Life (2015 IEEE ALIFE). Cape Town, South Africa; 2015. (317 KB)
(317 KB). Time consistent estimation of End-effectors from RGB-D data. In Image and Video Technology: 7th Pacific-Rim Symposium, PSIVT 2015, Auckland, New Zealand, November 25-27, 2015, Revised Selected Papers. Cham: Springer International Publishing; 2015. pp. 529-543. (2.22 MB)
(2.22 MB). UPC System for the 2015 MediaEval Multimodal Person Discovery in Broadcast TV task. In MediaEval 2015 Workshop. Wurzen, Germany; 2015. (163.11 KB)
(163.11 KB). UPC-UB-STP @ MediaEval 2015 Diversity Task: Iterative Reranking of Relevant Images. In MediaEval 2015 Workshop. 2015. (158.17 KB)
(158.17 KB). On the use of binary partition trees for the tree crown segmentation of tropical rainforest hyperspectral images. Remote Sensing of Environment. 2015;159:318-331. (3.06 MB)
(3.06 MB). Visual Information Retrieval in Endoscopic Video Archives. In IEEE/ACM International Workshop on Content-Based Multimedia Indexing - CBMI 2015 . Prague, Czech Republic; 2015. (1.67 MB)
(1.67 MB). Visual Saliency Prediction using Deep learning Techniques. . 2015. (1.57 MB)
(1.57 MB). Visual Search for Musical Performances and Endoscopic Videos. . 2015. (12.35 MB)
(12.35 MB). Visual Summary of Egocentric Photostreams by Representative Keyframes. . 2015. (1.36 MB)
(1.36 MB). Visual Summary of Egocentric Photostreams by Representative Keyframes. In IEEE International Workshop on Wearable and Ego-vision Systems for Augmented Experience (WEsAX) 2015. Turin, Italy; 2015. (2.69 MB)
(2.69 MB). 3D Shape Reconstruction from a Humanoid Generated Video Sequence. In IEEE International Conference on Humanoid Robots. Madrid; 2014. (4.61 MB)
(4.61 MB). Bundling interest points for object classification. . 2014. (2.15 MB)
(2.15 MB). Click’n’Cut: Crowdsourced Interactive Segmentation with Object Candidates. In 3rd International ACM Workshop on Crowdsourcing for Multimedia (CrowdMM). Orlando, Florida (USA); 2014. (1017.73 KB)
(1017.73 KB). Contextless Object Recognition with Shape-enriched SIFT and Bags of Features. . 2014. (4.82 MB)
(4.82 MB). Depth order estimation for video frames using motion occlusions. IET Computer Vision. 2014;8(2):152-160. (910.25 KB)
(910.25 KB). Efficient combination of pairwise feature networks. JMLR: Workshop and Conference Proceedings . Nancy, France: JMLR: Workshop and Conference Proceedings; 2014;46:77 - 84. (217.39 KB)
(217.39 KB)