Related papers: Predicate Classification Using Optimal Transport L…

Scene graph generation (SGG) has gained tremendous progress in recent years. However, its underlying long-tailed distribution of predicate classes is a challenging problem. For extremely unbalanced predicate distributions, existing…

The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e.g., "woman-on/standing on/walking on-beach" or "woman-near/looking at/in front of-child". While general SGG models are…

Scene Graph Generation (SGG) aims to represent visual scenes by identifying objects and their pairwise relationships, providing a structured understanding of image content. However, inherent challenges like long-tailed class distributions…

Scene graph generation (SGG) models have suffered from inherent problems regarding the benchmark datasets such as the long-tailed predicate distribution and missing annotation problems. In this work, we aim to alleviate the long-tailed…

Predicting the supply and demand of transport systems is vital for efficient traffic management, control, optimization, and planning. For example, predicting where from/to and when people intend to travel by taxi can support fleet managers…

Scene graph parsing aims to detect objects in an image scene and recognize their relations. Recent approaches have achieved high average scores on some popular benchmarks, but fail in detecting rare relations, as the highly long-tailed…

Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior…

Advanced graph neural networks have shown great potentials in graph classification tasks recently. Different from node classification where node embeddings aggregated from local neighbors can be directly used to learn node labels, graph…

The scene graph is a new data structure describing objects and their pairwise relationship within image scenes. As the size of scene graph in vision applications grows, how to losslessly and efficiently store such data on disks or transmit…

The notion of task similarity is at the core of various machine learning paradigms, such as domain adaptation and meta-learning. Current methods to quantify it are often heuristic, make strong assumptions on the label sets across the tasks,…

Scene graphs provide valuable information to many downstream tasks. Many scene graph generation (SGG) models solely use the limited annotated relation triples for training, leading to their underperformance on low-shot (few and zero)…

In machine learning and computer vision, optimal transport has had significant success in learning generative models and defining metric distances between structured and stochastic data objects, that can be cast as probability measures. The…

When learning graph neural networks (GNNs) in node-level prediction tasks, most existing loss functions are applied for each node independently, even if node embeddings and their labels are non-i.i.d. because of their graph structures. To…

Training scene graph classification models requires a large amount of annotated image data. Meanwhile, scene graphs represent relational knowledge that can be modeled with symbolic data from texts or knowledge graphs. While image annotation…

Scene graph prediction --- classifying the set of objects and predicates in a visual scene --- requires substantial training data. However, most predicates only occur a handful of times making them difficult to learn. We introduce the first…

Optimal transport provides a robust framework for comparing probability distributions. Its effectiveness is significantly influenced by the choice of the underlying ground metric. Traditionally, the ground metric has either been (i)…

With the recent promising results of contrastive learning in the self-supervised learning paradigm, supervised contrastive learning has successfully extended these contrastive approaches to supervised contexts, outperforming cross-entropy…

Causal discovery in the presence of missing data introduces a chicken-and-egg dilemma. While the goal is to recover the true causal structure, robust imputation requires considering the dependencies or, preferably, causal relations among…

The typical way for relation extraction is fine-tuning large pre-trained language models on task-specific datasets, then selecting the label with the highest probability of the output distribution as the final prediction. However, the usage…

Despite the great success object detection and segmentation models have achieved in recognizing individual objects in images, performance on cognitive tasks such as image caption, semantic image retrieval, and visual QA is far from…