5 accepted papers
Generating realistic and physically plausible 3D Human-Object Interactions (HOI) remains a key challenge in motion generation. One primary reason is that describing these physical constraints with words alone is difficult. To address this limitation, we propose a new paradigm: extracting rich intera
Graph Structure Learning (GSL) recently has attracted considerable attentions. Existing GSL methods assume that nodes with high attribute similarity belong to the same class. However, our experiments have found that the performance of similarity-based GSL methods decreases in cases of topology-imbal…
Human-object interaction (HOI) synthesis is crucial for creating immersive and realistic experiences for applications such as virtual reality. Existing methods often rely on simplified object representations, such as the object's centroid or the nearest point to a human, to achieve physically plausi…
Graph Neural Networks (GNNs) have been successful in modeling homophily graphs, but their performance is limited when applied to heterophily graphs. Some methods based on the LSTM can mitigate this issue while they artificially fix the input sequence which is reversed from the collection order of th…
A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network width is increased. Recent evidence suggests that developing compressible representations allows the complexity of large networks to be adjusted for the learning task…