{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:42:54Z","timestamp":1779381774404,"version":"3.53.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>The objective in image co-segmentation is to jointly\nsegment unknown common objects from a given\nset of images. In this paper, we propose a novel\ndeep convolution neural network based end-to-end\nco-segmentation model. It is composed of a metric\nlearning and decision network leading to a novel\nconditional siamese encoder-decoder network for\nestimating a co-segmentation mask. The role of the\nmetric learning network is to find an optimum latent\nfeature space where objects of the same class\nare closer and that of different classes are separated\nby a certain margin. Depending on the\nextracted features, the decision network decides\nwhether input images have common objects or not\nand the encoder-decoder network produces a cosegmentation\nmask accordingly. Key aspects of the\narchitecture are as follows. First, it is completely\nclass agnostic and does not require any semantic\ninformation. Second, in addition to producing\nmasks, the decoder network also learns similarity\nacross image pairs that improves co-segmentation\nsignificantly. Experimental results reflect an excellent\nperformance of our method compared to state of-the-art\nmethods on challenging co-segmentation\ndatasets.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/95","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"673-679","source":"Crossref","is-referenced-by-count":13,"title":["CoSegNet: Image Co-segmentation using a Conditional Siamese Convolutional Network"],"prefix":"10.24963","author":[{"given":"Sayan","family":"Banerjee","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Bombay, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avik","family":"Hati","sequence":"additional","affiliation":[{"name":"Istituto Italiano di Tecnologia, Genova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhasis","family":"Chaudhuri","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Bombay, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajbabu","family":"Velmurugan","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Bombay, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:44Z","timestamp":1564300004000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/95"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/95","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}