Related papers: MGDIL: Multi-Granularity Summarization and Domain-…

Benefiting from the powerful expressive capability of graphs, graph-based approaches have achieved impressive performance in various biomedical applications. Most existing methods tend to define the adjacency matrix among samples manually…

Domain Generalization (DG) aims to train a model, from multiple observed source domains, in order to perform well on unseen target domains. To obtain the generalization capability, prior DG approaches have focused on extracting…

Semantic location prediction aims to derive meaningful location insights from multimodal social media posts, offering a more contextual understanding of daily activities than using GPS coordinates. This task faces significant challenges due…

We propose a novel approach for domain generalisation (DG) leveraging risk distributions to characterise domains, thereby achieving domain invariance. In our findings, risk distributions effectively highlight differences between training…

Domain generalization (DG) intends to train a model on multiple source domains to ensure that it can generalize well to an arbitrary unseen target domain. The acquisition of domain-invariant representations is pivotal for DG as they possess…

Recently, large multimodal models have built a bridge from visual to textual information, but they tend to underperform in remote sensing scenarios. This underperformance is due to the complex distribution of objects and the significant…

Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually,…

Recently, multimodal contrastive learning (MMCL) approaches, such as CLIP, have achieved a remarkable success in learning representations that are robust against distribution shift and generalize to new domains. Despite the empirical…

Domain generalization (DG) aims to learn domain-generalizable models from one or multiple source domains that can perform well in unseen target domains. Despite its recent progress, most existing work suffers from the misalignment between…

Human beings are able to understand objectives and learn by simply observing others perform a task. Imitation learning methods aim to replicate such capabilities, however, they generally depend on access to a full set of optimal states and…

The ability to deploy robots that can operate safely in diverse environments is crucial for developing embodied intelligent agents. As a community, we have made tremendous progress in within-domain LiDAR semantic segmentation. However, do…

It is significantly challenging to recognize daily human actions in homes due to the diversity and dynamic changes in unconstrained home environments. It spurs the need to continually adapt to various users and scenes. Fine-tuning current…

Accurately predicting molecular properties is a challenging but essential task in drug discovery. Recently, many mono-modal deep learning methods have been successfully applied to molecular property prediction. However, the inherent…

RGB-Infrared person re-identification (RGB-IR ReID) aims to associate people across disjoint RGB and IR camera views. Currently, state-of-the-art performance of RGB-IR ReID is not as impressive as that of conventional ReID. Much of that is…

Recently, learning-based stereo matching methods have achieved great improvement in public benchmarks, where soft argmin and smooth L1 loss play a core contribution to their success. However, in unsupervised domain adaptation scenarios, we…

Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags. However, due to their weak supervision nature, the MIL methods were susceptible…

In this paper, we consider cross-domain imitation learning (CDIL) in which an agent in a target domain learns a policy to perform well in the target domain by observing expert demonstrations in a source domain without accessing any reward…

Vehicle re-identification (Vehicle ReID) aims at retrieving vehicle images across disjoint surveillance camera views. The majority of vehicle ReID research is heavily reliant upon supervisory labels from specific human-collected datasets…

We investigate the generalization boundaries of current Multimodal Large Language Models (MLLMs) via comprehensive evaluation under out-of-distribution scenarios and domain-specific tasks. We evaluate their zero-shot generalization across…

Real world images frequently exhibit multiple overlapping biases, including textures, watermarks, gendered makeup, scene object pairings, etc. These biases collectively impair the performance of modern vision models, undermining both their…