S Zhang, X Feng, W Fan, W Fang, F Feng… - Proceedings of the …, 2023 - ojs.aaai.org
Existing video-audio understanding models are trained and evaluated in an intra-domain setting, facing performance degeneration in real-world applications where multiple domains …
Long-tailed learning has attracted much attention recently, with the goal of improving generalisation for tail classes. Most existing works use supervised learning without …
B Zhu, Y Niu, XS Hua, H Zhang - … of the AAAI conference on artificial …, 2022 - ojs.aaai.org
We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of" tail" over" …
In the real world, large-scale datasets for visual recognition typically exhibit a long-tailed distribution, where only a few classes contain adequate samples but the others have (much) …
Major advancements have been made in the field of object detection and segmentation recently. However, when it comes to rare categories, the state-of-the-art methods fail to …
X Deng, Z Zhang - Advances in Neural Information …, 2021 - proceedings.neurips.cc
Abstract Knowledge distillation (KD) addresses model compression by distilling knowledge from a large model (teacher) to a smaller one (student). The existing distillation approaches …
Large-scale object detection and instance segmentation face a severe data imbalance. The finer-grained object classes become, the less frequent they appear in our datasets …
Graph Convolutional Network (GCN) is an emerging technique for information retrieval (IR) applications. While GCN assumes the homophily property of a graph, real-world graphs are …
C Ge, S Song, G Huang - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Human trajectory Prediction (HTP) in complex social environments plays a crucial and fundamental role in artificial intelligence systems. Conventional methods make use of both …