Related papers: A Comparative Study of Training Objectives for Cla…
We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features. There are different ways…
Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…
In response to rising societal awareness of privacy concerns, face anonymization techniques have advanced, including the emergence of face-swapping methods that replace one identity with another. Achieving a balance between anonymity and…
Spotting facial micro-expression from videos finds various potential applications in fields including clinical diagnosis and interrogation, meanwhile this task is still difficult due to the limited scale of training data. To solve this…
Face recognition and verification are two computer vision tasks whose performance has progressed with the introduction of deep representations. However, ethical, legal, and technical challenges due to the sensitive character of face data…
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional,…
Analysis of faces is one of the core applications of computer vision, with tasks ranging from landmark alignment, head pose estimation, expression recognition, and face recognition among others. However, building reliable methods requires…
Understanding how the brain encodes stimuli has been a fundamental problem in computational neuroscience. Insights into this problem have led to the design and development of artificial neural networks that learn representations by…
The self-supervised objective of masking-and-predicting has led to promising performance gains on a variety of downstream tasks. However, while most approaches randomly mask tokens, there is strong intuition that deciding what to mask can…
Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?". The comparison of this instance before and after…
In traditional Visual Question Generation (VQG), most images have multiple concepts (e.g. objects and categories) for which a question could be generated, but models are trained to mimic an arbitrary choice of concept as given in their…
Generation of stroke-based non-photorealistic imagery, is an important problem in the computer vision community. As an endeavor in this direction, substantial recent research efforts have been focused on teaching machines "how to paint", in…
The goal of this paper is to synthesise talking faces with controllable facial motions. To achieve this goal, we propose two key ideas. The first is to establish a canonical space where every face has the same motion patterns but different…
Unified multimodal models integrate the reasoning capacity of large language models with both image understanding and generation, showing great promise for advanced multimodal intelligence. However, the community still lacks a rigorous…
Counterfactual explanations assess unfairness by revealing how inputs must change to achieve a desired outcome. This paper introduces the first graph-based framework for generating group counterfactual explanations to audit group fairness,…
Person attribute recognition and attribute-based retrieval are two core human-centric tasks. In the recognition task, the challenge is specifying attributes depending on a person's appearance, while the retrieval task involves searching for…
Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model's ability to…
Self-supervised pre-training, such as BERT, MASS and BART, has emerged as a powerful technique for natural language understanding and generation. Existing pre-training techniques employ autoencoding and/or autoregressive objectives to train…
Face image synthesis has progressed beyond the point at which humans can effectively distinguish authentic faces from synthetically generated ones. Recently developed synthetic face image detectors boast "better-than-human" discriminative…
Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a…