Related papers: Domain Knowledge Driven Pseudo Labels for Interpre…

Weakly-supervised temporal action localization is a problem of learning an action localization model with only video-level action labeling available. The general framework largely relies on the classification activation, which employs an…

This paper aims to tackle the interactive behavior prediction task, and proposes a novel Conditional Goal-oriented Trajectory Prediction (CGTP) framework to jointly generate scene-compliant trajectories of two interacting agents. Our CGTP…

New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either…

Imitation learning holds great promise for addressing the complex task of autonomous urban driving, as experienced human drivers can navigate highly challenging scenarios with ease. While behavior cloning is a widely used imitation learning…

In this paper, we study the task of embodied interactive learning for object detection. Given a set of environments (and some labeling budget), our goal is to learn an object detector by having an agent select what data to obtain labels…

Autonomous vehicles (AVs) must be both safe and trustworthy to gain social acceptance and become a viable option for everyday public transportation. Explanations about the system behaviour can increase safety and trust in AVs.…

With the unprecedented shift towards automated urban environments in recent years, a new paradigm is required to study pedestrian behaviour. Studying pedestrian behaviour in futuristic scenarios requires modern data sources that consider…

Pre-trained language models have achieved promising performance on general benchmarks, but underperform when migrated to a specific domain. Recent works perform pre-training from scratch or continual pre-training on domain corpora. However,…

Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to…

Graph representation learning is a fundamental research issue in various domains of applications, of which the inductive learning problem is particularly challenging as it requires models to generalize to unseen graph structures during…

Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is…

Multi-label image classification is a prediction task that aims to identify more than one label from a given image. This paper considers the semantic consistency of the latent space between the visual patch and linguistic label domains and…

Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive…

We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to…

End-to-end autonomous driving has emerged as a compelling alternative to traditional modular pipelines by directly mapping raw sensor data to driving actions. While recent approaches achieve strong performance on single-domain datasets,…

Image captioning models generally lack the capability to take into account user interest, and usually default to global descriptions that try to balance readability, informativeness, and information overload. On the other hand, VQA models…

Most of the recent Deep Semantic Segmentation algorithms suffer from large generalization errors, even when powerful hierarchical representation models based on convolutional neural networks have been employed. This could be attributed to…

We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen…

In this paper, we present a novel trajectory prediction model for autonomous driving, combining a Characterized Diffusion Module and a Spatial-Temporal Interaction Network to address the challenges posed by dynamic and heterogeneous traffic…

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer,…