Anton van den Hengel

• PhD
• Professor at The University of Adelaide

As the number of individuals in a crowd grows, enumeration-based techniques become increasingly infeasible and their estimates increasingly unreliable. We propose instead an estimation-based version of the problem: we label Rough Crowd Counting that delivers better accuracy on the basis of training data that is easier to acquire. Rough crowd counti...

Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that the exemplar image-text pairs constitute two representations of an identical concept. However, recent research h...

Zero-shot video captioning requires that a model generate high-quality captions without human-annotated video-text pairs for training. State-of-the-art approaches to the problem leverage CLIP to extract visual-relevant textual prompts to guide language models in generating captions. These methods tend to focus on one key aspect of the scene and bui...

Diagrams serve as a fundamental form of visual language, representing complex concepts and their inter-relationships through structured symbols, shapes, and spatial arrangements. Unlike natural images, their inherently symbolic and abstract nature poses significant challenges for Multimodal Large Language Models (MLLMs). However, current benchmarks...

Recovering the underlying Directed Acyclic Graph (DAG) structures from observational data presents a formidable challenge, partly due to the combinatorial nature of the DAG-constrained optimization problem. Recently, researchers have identified gradient vanishing as one of the primary obstacles in differentiable DAG learning and have proposed sever...

Text-video prediction (TVP) is a downstream video generation task that requires a model to produce subsequent video frames given a series of initial video frames and text describing the required motion. In practice TVP methods focus on a particular category of videos depicting manipulations of objects carried out by human beings or robot arms. Prev...

Movie dubbing describes the process of transforming a script into speech that aligns temporally and emotionally with a given movie clip while exemplifying the speaker's voice demonstrated in a short reference audio clip. This task demands the model bridge character performances and complicated prosody structures to build a high-quality video-synchr...

The remarkable achievements of large language models (LLMs) have led many to conclude that they exhibit a form of intelligence. This is as opposed to explanations of their capabilities based on their ability to perform relatively simple manipulations of vast volumes of data. To illuminate the distinction between these explanations, we introduce a n...

The ability to interpret and intervene model decisions is important for the adoption of computer-aided diagnosis methods in clinical workflows. Recent concept-based methods link the model predictions with interpretable concepts and modify their activation scores to interact with the model. However, these concepts are at the image level, which hinde...

Low-Rank Adaptation (LoRA) and its variants have shown impressive results in reducing the number of trainable parameters and memory requirements of large transformer networks while maintaining fine-tuning performance. However, the low-rank nature of the weight update inherently limits the representation power of fine-tuned models, potentially compr...

Current multimodal large language models (MLLMs) often underperform on mathematical problem-solving tasks that require fine-grained visual understanding. The limitation is largely attributable to inadequate perception of geometric primitives during image-level contrastive pre-training (e.g., CLIP). While recent efforts to improve math MLLMs have fo...

Given a piece of text, a video clip, and a reference audio, the movie dubbing task aims to generate speech that aligns with the video while cloning the desired voice. The existing methods have two primary deficiencies: (1) They struggle to simultaneously hold audio-visual sync and achieve clear pronunciation; (2) They lack the capacity to express u...

Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data. Their applications are versatile and have the potential to improve diagnostic accuracy and decision-making for individual patients while also contributing to enhanced pub...

Automated hate speech detection is an important tool in combating the spread of hate speech, particularly in social media. Numerous methods have been developed for the task, including a recent proliferation of deep-learning based approaches. A variety of datasets have also been developed, exemplifying various manifestations of the hate-speech detec...

Accurately predicting stock returns is crucial for effective portfolio management. However, existing methods often overlook a fundamental issue in the market, namely, distribution shifts, making them less practical for predicting future markets or newly listed stocks. This study introduces a novel approach to address this challenge by focusing on t...

Background Robust and accurate prediction of cardiovascular disease (CVD) risk facilitates early intervention to benefit patients. The intricate relationship between mental health disorders and CVD is widely recognized. However, existing models often overlook psychological factors, relying on a limited set of clinical and lifestyle parameters, or b...

One of the significant challenges in reinforcement learning (RL) when dealing with noise is estimating latent states from observations. Causality provides rigorous theoretical support for ensuring that the underlying states can be uniquely recovered through identifiability. Consequently, some existing work focuses on establishing identifiability fr...

The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box concern of DNNs. While CLIP provides both explainability and zero-shot classification capability, its pre-training...

Automatically generating symbolic music-music scores tailored to specific human needs-can be highly beneficial for musicians and enthusiasts. Recent studies have shown promising results using extensive datasets and advanced transformer architectures. However, these state-of-the-art models generally offer only basic control over aspects like tempo a...

Pre-trained models produce strong generic representations that can be adapted via fine-tuning. The learned weight difference relative to the pre-trained model, known as a task vector, characterises the direction and stride of fine-tuning. The significance of task vectors is such that simple arithmetic operations on them can be used to combine diver...

Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning. Various architectures, from vision transformers (ViTs) to convolutional networks (ResNets) have been trained with CLIP to serve as general solutions to diverse vision tasks. This paper explores the differences across various CLIP-traine...

The state-of-the-art semantic segmentation methods have achieved impressive performance on predefined close-set individual datasets, but their generalization to zero-shot domains and unseen categories is limited. Labeling a large-scale dataset is challenging and expensive, Training a robust semantic segmentation model on multi-domains has drawn muc...

Crowd localization aims to predict the positions of humans in images of crowded scenes. While existing methods have made significant progress, two primary challenges remain: (i) a fixed number of evenly distributed anchors can cause excessive or insufficient predictions across regions in an image with varying crowd densities, and (ii) ranking incon...

Inferring the 3D structure of a non-rigid dynamic scene from a single moving camera is an under-constrained problem. Inspired by the remarkable progress of neural radiance fields (NeRFs) in photo-realistic novel view synthesis of static scenes, it has also been extended to dynamic settings. Such methods heavily rely on implicit neural priors to reg...

Generalized zero-shot learning (GZSL) requires that models are able to recognize classes they were trained on, and new classes they haven’t seen before. Feature-generation approaches are popular due to their effectiveness in mitigating overfitting to the training classes. Existing generative approaches usually adopt simple discriminators for distri...

This paper offers a new perspective to ease the challenge of domain generalization, which involves maintaining robust results even in unseen environments. Our design focuses on the decision-making process in the final classifier layer. Specifically, we propose treating the element-wise contributions to the final results as the rationale for making...

Gaussian process (GP) based Bayesian optimization (BO) is a powerful method for optimizing black-box functions efficiently. The practical performance and theoretical guarantees associated with this approach depend on having the correct GP hyperparameter values, which are usually unknown in advance and need to be estimated from the observed data. Ho...

Rotated bounding boxes drastically reduce output ambiguity of elongated objects, making it superior to axis-aligned bounding boxes. Despite the effectiveness, rotated detectors are not widely employed. Annotating rotated bounding boxes is such a laborious process that they are not provided in many detection datasets where axis-aligned annotations a...

Metric learning is a fundamental problem in computer vision whereby a model is trained to learn a semantically useful embedding space via ranking losses. Traditionally, the effectiveness of a ranking loss depends on the minibatch size, and is, therefore, inherently limited by the memory constraints of the underlying hardware. While simply accumulat...

Self-supervised learning (SSL) strategies have demonstrated remarkable performance in various recognition tasks. However, both our preliminary investigation and recent studies suggest that they may be less effective in learning representations for fine-grained visual recognition (FGVR) since many features helpful for optimizing SSL objectives are n...

Reasoning the 3D structure of a non-rigid dynamic scene from a single moving camera is an under-constrained problem. Inspired by the remarkable progress of neural radiance fields (NeRFs) in photo-realistic novel view synthesis of static scenes, extensions have been proposed for dynamic settings. These methods heavily rely on neural priors in order...

The ability to use inductive reasoning to extract general rules from multiple observations is a vital indicator of intelligence. As humans, we use this ability to not only interpret the world around us, but also to predict the outcomes of the various interactions we experience. Generalising over multiple observations is a task that has historically...

Self-supervised learning (SSL) aims to produce useful feature representations without access to any human-labeled data annotations. Due to the success of recent SSL methods based on contrastive learning, such as SimCLR, this problem has gained popularity. Most current contrastive learning approaches append a parametrized projection head to the end...

We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression mapping from images to the keypoint coordinates, without resorting to intermediate representations such as heatma...

The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction f...

Background Robust and accurate prediction of cardiovascular disease (CVD) risk facilitates early intervention to benefit patients. It is well-known that mental disorders and CVD are interrelated. Nevertheless, psychological factors are not considered in existing models, which use either a limited number of clinical and lifestyle factors, or have be...

In this paper, we come up with a simple yet effective approach for instance segmentation on 3D point cloud with strong robustness. Previous top-performing methods for this task adopt a bottom-up strategy, which often involves various inefficient operations or complex pipelines, such as grouping over-segmented components, introducing heuristic post-...

Causal representation learning exposes latent high-level causal variables behind low-level observations, which has enormous potential for a set of downstream tasks of interest. Despite this, identifying the true latent causal representation from observed data is a great challenge. In this work we focus on identifying latent causal variables. To thi...

Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge, particularly for dense prediction. In this paper we propose a content-based sparse attention method, as an alternative to dense self-attention, aiming to reduce the com...

The availability of clean and diverse labeled data is a major roadblock for training models on complex tasks such as visual question answering (VQA). The extensive work on large vision-and-language models has shown that self-supervised learning is effective for pretraining multimodal interactions. In this technical report, we focus on visual repres...

Semi-supervised learning is a critical tool in reducing machine learning's dependence on labeled data. It has, however, been applied primarily to image and language data, by exploiting the inherent spatial and semantic structure therein. These methods do not apply to tabular data because these domain structures are not available. Existing pseudo-la...

A wide variety of methods have been developed for identifying depression, but they focus primarily on measuring the degree to which individuals are suffering from depression currently. In this work we explore the possibility of predicting future depression using machine learning applied to longitudinal socio-demographic data. In doing so we show th...

The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics. In contrast, we propose a fully-convolutional 3D point cloud instance segmentation method that works in a per-point prediction f...

Convolutional neural networks (CNNs) have gained significant popularity in orthopedic imaging in recent years due to their ability to solve fracture classification problems. A common criticism of CNNs is their opaque learning and reasoning process, making it difficult to trust machine diagnosis and the subsequent adoption of such algorithms in clin...

The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g. images, videos) and in low-data regimes. In this paper, we propose a novel method for batch AL called ALFA-Mix. We...

The study of robustness has received much attention due to its inevitability in data-driven settings where many systems face uncertainty. One such example of concern is Bayesian Optimization (BO), where uncertainty is multi-faceted, yet there only exists a limited number of works dedicated to this direction. In particular, there is the work of Kirs...

Convolutional neural networks (CNNs) have gained significant popularity in orthopedic imaging in recent years due to their ability to solve fracture classification problems. A common criticism of CNNs is their opaque learning and reasoning process, making it difficult to trust machine diagnosis and the subsequent adoption of such algorithms in clin...

We introduce Retrieval Augmented Classification (RAC), a generic approach to augmenting standard image classification pipelines with an explicit retrieval module. RAC consists of a standard base image encoder fused with a parallel retrieval branch that queries a non-parametric external memory of pre-encoded images and associated text snippets. We a...

Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. Despite their performance, th...

Automated hate speech detection is an important tool in combating the spread of hate speech, particularly in social media. Numerous methods have been developed for the task, including a recent proliferation of deep-learning based approaches. A variety of datasets have also been developed, exemplifying various manifestations of the hate-speech detec...

We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic segmentation datasets, without training on those datasets. This is achieved by replacing each class label wit...

Obtaining a high dynamic range (HDR) image from multiple low dynamic range images with different exposures is an important step in various computer vision tasks. One of the ongoing challenges in the field is to generate HDR images without ghosting artifacts. Motivated by an observation that such artifacts are particularly noticeable in the gradient...

We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression mapping from images to the keypoint coordinates, without resorting to intermediate representations such as heatma...

Ghosting artifacts caused by moving objects and misalignments are a key challenge in constructing high dynamic range (HDR) images. Current methods first register the input low dynamic range (LDR) images using optical flow before merging them. This process is error-prone, and often causes ghosting in the resulting merged image. We propose a novel du...

Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs. One of the challenges in GAD is to devise graph representations that enable the detection of both locally- and globally-anomalous graphs, i.e., graphs that are abnormal i...

Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in discriminating anomalies from normal samples due to the lack of the knowledge about the anomalies. Here, we study the probl...

We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. This enables it to adapt, at inference, to varying feature and object scales. Doing so avoids some pitfalls of bottom up approaches, including a dependence on hyper-parameter tuning and heuristic post-processing pipelines to compensate for the inevita...

Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution (OOD). The more complex the task to learn, the more likely it is that statistical artifacts (i.e. selection biases,...

Vision-and-Language Navigation (VLN) requires an agent to navigate to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas. Most existing methods take words in instructions and discrete views of each panorama as the minimal unit of encoding. However, this requires a model to match different textual...

Negotiation, as an essential and complicated aspect of online shopping, is still challenging for an intelligent agent. To that end, we propose the Price Negotiator , a modular deep neural network that addresses the unsolved problems in recent studies by (1) considering images of the items as a crucial, though neglected, source of information in a...

Anomaly detection, a.k.a. outlier detection or novelty detection, has been a lasting yet active research area in various research communities for several decades. There are still some unique problem complexities and challenges that require advanced approaches. In recent years, deep learning enabled anomaly detection, i.e., deep anomaly detection ,...

Visual navigation is often cast as a reinforcement learning (RL) problem. Current methods typically result in a suboptimal policy that learns general obstacle avoidance and search behaviours. For example, in the target-object navigation setting, the policies learnt by traditional methods often fail to complete the task, even when the target is clea...

Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods learned on synthetic data do not perform well in real-world, due to the domain gap between the artificially synthesized and real LR images. Some efforts are thus taken t...

The limits of applicability of vision-and-language models are defined by the coverage of their training data. Tasks like vision question answering (VQA) often require commonsense and factual information beyond what can be learned from task-specific datasets. This paper investigates the injection of knowledge from general-purpose knowledge bases (KB...

Depression is among the most prevalent mental disorders, affecting millions of people of all ages globally. Machine learning techniques have shown effective in enabling automated detection and prediction of depression for early intervention and treatment. However, they are challenged by the relative scarcity of instances of depression in the data....

Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions. The inevitable variation in the instance scales can l...

Vision-and-Language Navigation (VLN) is unique in that it requires turning relatively general natural-language instructions into robot agent actions, on the basis of visible environments. This requires to extract value from two very different types of natural-language information. The first is object description (e.g., ‘table’, ‘door’), each presen...

One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be addressed by simply using more data from the same distribution. We propose an auxiliary training objective that...

Density estimation is a challenging unsupervised learning problem. Current maximum likelihood approaches for density estimation are either restrictive or incapable of producing high-quality samples. On the other hand, likelihood-free models such as generative adversarial networks, produce sharp samples without a density model. The lack of a density...

We address a critical yet largely unsolved anomaly detection problem, in which we aim to learn detection models from a small set of partially labeled anomalies and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either proceed unsupervised with the unlabeled data, or exclusively fi...