Abstract | ||
---|---|---|
Different from after-the-fact action recognition, action prediction task requires action labels to be predicted from partially observed videos containing incomplete action executions. It is challenging because these partial videos have insufficient discriminative information, and their temporal structure is damaged. We study this problem in this paper, and propose an efficient and powerful deep ne... |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/TPAMI.2018.2882805 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | Field | DocType |
Videos,Feature extraction,Decoding,Accidents,Prediction methods,Training,Task analysis | Autoencoder,Pattern recognition,Computer science,Action recognition,Exploit,Artificial intelligence,Decoding methods,Classifier (linguistics),Discriminative model,Adversarial system,Speedup | Journal |
Volume | Issue | ISSN |
42 | 3 | 0162-8828 |
Citations | PageRank | References |
4 | 0.42 | 22 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu Kong | 1 | 412 | 24.72 |
Zhiqiang Tao | 2 | 142 | 12.05 |
Yun Fu | 3 | 4267 | 208.09 |