Related papers: Generalized Unbiased Scene Graph Generation
Robotic manipulation tasks, such as object rearrangement, play a crucial role in enabling robots to interact with complex and arbitrary environments. Existing work focuses primarily on single-level rearrangement planning and, even if…
We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality of synthesized images is far from satisfactory due to three…
Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…
Generalized Category Discovery (GCD) aims to identify novel categories in unlabeled data while leveraging a small labeled subset of known classes. Training a parametric classifier solely on image features often leads to overfitting to old…
Time series anomaly prediction plays an essential role in many real-world scenarios, such as environmental prevention and prompt maintenance of cyber-physical systems. However, existing time series anomaly prediction methods mainly require…
By treating users' interactions as a user-item graph, graph learning models have been widely deployed in Collaborative Filtering(CF) based recommendation. Recently, researchers have introduced Graph Contrastive Learning(GCL) techniques into…
In this work, we devote ourselves to the challenging task of Unsupervised Multi-view Representation Learning (UMRL), which requires learning a unified feature representation from multiple views in an unsupervised manner. Existing UMRL…
Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize…
Graph contrastive learning (GCL) has garnered significant attention recently since it learns complex structural information from graphs through self-supervised learning manner. However, prevalent GCL models may suffer from performance…
There has been exciting progress in generating images from natural language or layout conditions. However, these methods struggle to faithfully reproduce complex scenes due to the insufficient modeling of multiple objects and their…
Recently, increasing efforts have been focused on Weakly Supervised Scene Graph Generation (WSSGG). The mainstream solution for WSSGG typically follows the same pipeline: they first align text entities in the weak image-level supervisions…
Multi-view subspace clustering (MSC) is a popular unsupervised method by integrating heterogeneous information to reveal the intrinsic clustering structure hidden across views. Usually, MSC methods use graphs (or affinity matrices) fusion…
Scene graph generation (SGG) is an important task in image understanding because it represents the relationships between objects in an image as a graph structure, making it possible to understand the semantic relationships between objects…
Despite recent advancements in single-domain or single-object image generation, it is still challenging to generate complex scenes containing diverse, multiple objects and their interactions. Scene graphs, composed of nodes as objects and…
Federated Graph Learning (FGL) enables collaborative learning over distributed graph data, yet existing approaches largely rely on a closed-world assumption, limiting their applicability in dynamic environments where novel categories…
Multimodal Domain Generalization (MMDG) leverages the complementary strengths of multiple modalities to enhance model generalization on unseen domains. A central challenge in multimodal learning is optimization imbalance, where modalities…
Generalized category discovery (GCD) is a recently proposed open-world problem, which aims to automatically cluster partially labeled data. The main challenge is that the unlabeled data contain instances that are not only from known…
Since annotating medical images for segmentation tasks commonly incurs expensive costs, it is highly desirable to design an annotation-efficient method to alleviate the annotation burden. Recently, contrastive learning has exhibited a great…
Synthesizing consistent and photorealistic 3D scenes is an open problem in computer vision. Video diffusion models generate impressive videos but cannot directly synthesize 3D representations, i.e., lack 3D consistency in the generated…
Recognizing multiple labels of an image is a practical yet challenging task, and remarkable progress has been achieved by searching for semantic regions and exploiting label dependencies. However, current works utilize RNN/LSTM to…