{"id": "356b431d4f7a2a0a38cf971c84568207dcdbf189", "citations": [{"id": "dc5d04d34b278b944097b8925a9147773bbb80cc", "title": "A Temporal Sequence Learning for Action Recognition and Prediction", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354149", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00045", "http://doi.org/10.1109/WACV.2018.00045"]}, {"id": "7ec431e36919e29524eceb1431d3e1202637cf19", "title": "Object detection and tracking in crowd environment \u2014 A review", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8365242"]}, {"id": "c038beaa228aeec174e5bd52460f0de75e9cccbe", "title": "Temporal Segment Networks for Action Recognition in Videos", "year": "2018", "pdf": ["https://arxiv.org/pdf/1705.02953.pdf"], "doi": []}, {"id": "59d225486161b43b7bf6919b4a4b4113eb50f039", "title": "Complex Event Recognition from Images with Few Training Examples", "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.04769.pdf"], "doi": []}, {"id": "590628a9584e500f3e7f349ba7e2046c8c273fcf", "title": "Generating Natural Questions About an Image", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.06059.pdf"], "doi": []}, {"id": "60efdb2e204b2be6701a8e168983fa666feac1be", "title": "Transferring Deep Object and Scene Representations for Event Recognition in Still Images", "year": "2017", "pdf": ["http://www.vision.ee.ethz.ch/en/publications/papers/articles/eth_biwi_01387.pdf"], "doi": ["http://doi.org/10.1007/s11263-017-1043-5"]}, {"id": "0c53ef79bb8e5ba4e6a8ebad6d453ecf3672926d", "title": "Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition", "year": "2017", "pdf": ["https://arxiv.org/pdf/1609.00153.pdf"], "doi": []}, {"id": "28cd46a078e8fad370b1aba34762a874374513a5", "title": "cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06436.pdf"], "doi": []}, {"id": "7c3e09e0bd992d3f4670ffacb4ec3a911141c51f", "title": "Transferring Object-Scene Convolutional Neural Networks for Event Recognition in Still Images", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.00162.pdf"], "doi": []}, {"id": "48a6a1c6a0ac5f2b7912b3ccb40b0c07f62ddfdf", "title": "Event-enabled intelligent asset selection and grouping for photobook creation", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1016/j.imavis.2015.12.003"]}, {"id": "43261920d2615f135d6e72b333fe55d3f2659145", "title": "A Systematic Mapping Study of Computer Vision Approaches based on Deep Learning and Neural Network", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3136301"]}, {"id": "1886b6d9c303135c5fbdc33e5f401e7fc4da6da4", "title": "Knowledge Guided Disambiguation for Large-Scale Scene Classification With Multi-Resolution CNNs", "year": "2017", "pdf": ["https://arxiv.org/pdf/1610.01119.pdf"], "doi": []}, {"id": "d963bdff2ce5212fa585a83ca8fad96875bc0057", "title": "Combining multi-representation for multimedia event detection using co-training", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1016/j.neucom.2016.03.091"]}]}