The performance of current Scene Graph Generation (SGG) models is severely hampered by hard-to-distinguish predicates, e.g., woman-on/standing on/walking on-beach. As general SGG models tend to predict head predicates and re-balancing strategies prefer tail categories, none of them can appropriately handle hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating hard-to-distinguish objects, we propose an Adaptive Fine-Grained Predicates Learning (FGPL-A) which aims at differentiating hard-to-distinguish predicates for SGG. First, we introduce an Adaptive Predicate Lattice (PL-A) to figure out hard-to-distinguish predicates, which adaptively explores predicate correlations in keeping with model's dynamic learning pace. Practically, PL-A is initialized from SGG dataset, and gets refined by exploring model's predictions of current mini-batch. Utilizing PL-A, we propose an Adaptive Category Discriminating Loss (CDL-A) and an Adaptive Entity Discriminating Loss (EDL-A), which progressively regularize model's discriminating process with fine-grained supervision concerning model's dynamic learning status, ensuring balanced and efficient learning process. Extensive experimental results show that our proposed model-agnostic strategy significantly boosts performance of benchmark models on VG-SGG and GQA-SGG datasets by up to 175% and 76% on Mean Recall@100, achieving new state-of-the-art performance. Moreover, experiments on Sentence-to-Graph Retrieval and Image Captioning tasks further demonstrate practicability of our method.

Document Summarization (DS) aims to generate an abridged version of single or multiple topic-related texts as concise and coherent as possible while preserving the salient and factually consistent information [1]. The document summarization task with a single input document is known as the Single Document Summarization (SDS). By contrast, the Multi-Document Summarization (MDS) task emphasizes synthesizing a large number of topic-related documents to generate a compressed summary from various times and perspectives. In addition, there are two general methods in document summarization: 1) the Extractive Document Summarization (EDS) method respects the lexicon of the original text, regarding the summary formation is verbatim by key words and phrases selected from the source corpus; and 2) the Abstractive Document Summarization (ADS) method respects the semantics of the original text, regarding the summary construction is by rephrasing texts according to the comprehension of text substances. Generally, a document summarization model is to achieve the following goals [2]: G1. Coverage: A document summarization model aims to generate a comprehensive summary that covers all the main and noteworthy contents of the input text(s); G2. Non-redundancy: A document summarization model aims to generate a precise and concise summary without any redundant or meaninglessly repeated information; G3.

Pathologists have a rich vocabulary with which they can describe all the nuances of cellular morphology. In their world, there is a natural pairing of images and words. Recent advances demonstrate that machine learning models can now be trained to learn high-quality image features and represent them as discrete units of information. This enables natural language, which is also discrete, to be jointly modelled alongside the imaging, resulting in a description of the contents of the imaging. Here we present experiments in applying discrete modelling techniques to the problem domain of non-melanoma skin cancer, specifically, histological images of Intraepidermal Carcinoma (IEC). Implementing a VQ-GAN model to reconstruct high-resolution (256x256) images of IEC images, we trained a sequence-to-sequence transformer to generate natural language descriptions using pathologist terminology. Combined with the idea of interactive concept vectors available by using continuous generative methods, we demonstrate an additional angle of interpretability. The result is a promising means of working towards highly expressive machine learning systems which are not only useful as predictive/classification tools, but also means to further our scientific understanding of disease.

Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained models, substantial amounts of hallucinated content are found during the human evaluation. Pre-trained models are most commonly fine-tuned with cross-entropy loss for text summarization, which may not be an optimal strategy. In this work, we provide a typology of factual errors with annotation data to highlight the types of errors and move away from a binary understanding of factuality. We further propose a training strategy that improves the factual consistency and overall quality of summaries via a novel contrastive fine-tuning, called ConFiT. Based on our linguistically-informed typology of errors, we design different modular objectives that each target a specific type. Specifically, we utilize hard negative samples with errors to reduce the generation of factual inconsistency. In order to capture the key information between speakers, we also design a dialogue-specific loss. Using human evaluation and automatic faithfulness metrics, we show that our model significantly reduces all kinds of factual errors on the dialogue summarization, SAMSum corpus. Moreover, our model could be generalized to the meeting summarization, AMI corpus, and it produces significantly higher scores than most of the baselines on both datasets regarding word-overlap metrics.

Inflation is a global problem, and it's one that is being exacerbated by climate change. This is because the increased frequency and severity of extreme weather events drive up prices for food, energy, and other necessities. But there is hope: AI can help us fight climate change by reducing emissions, improving energy efficiency, and increasing the use of renewable energy sources. Therefore, the Green transition is a key pillar in fighting inflation, and AI is an important tool in this effort. In fact, according to a 2022 BCG Climate AI Survey report (shown below), 87% of private and public sector CEOs with decision-making power in AI and climate believe AI is an essential tool in the fight against climate change.

In the post-pandemic world, the onus seems to be on artificial intelligence (AI) to carry the healthcare sector forward. Maja Dragovic finds out how the attitudes towards AI in the sector have changed over the last 12 months. The focus on AI has definitely shifted since the pandemic, with data being seen as a tool to improve the health and care of a population in a safe, trusted and transparent way. The government's recent data strategy for health and care has set the direction for the use of data in a post-pandemic healthcare system with AI playing a significant role, especially in screening services where the technology can help scan numerous hospital images for irregularities. For Chris Scarisbrick, sales director at Sectra, an accelerator of AI use in screening was the development of the National Lung Screening pilot.

At the end of my Melbourne street there's a new system being installed for traffic management. I hadn't even noticed the extra cameras, vehicle and pedestrian sensors, LiDAR and radar on the intersection, but these tools are all part of a larger system, with researchers hoping that a 2.5km section of Nicholson Street, in Carlton, will eventually be run by an artificial intelligence (AI). This might sound a little nerve-wracking to the average commuter, but these "smart corridors" are popping up around the world – systems that promise to provide us with less traffic and better safety. "Many cities around the world have dedicated corridors or smart motorways that are equipped with sensors, CCTV cameras and AI for predicting the traffic flow, speed, or occupancy at a specific moment in time," says Dr Adriana-Simona Mihaita, an AI infrastructure researcher at the University of Technology Sydney, who was not involved in the research. "Accurate predictions will provide transport operators with the means to make informed decisions and apply new control plans, or adjust the current ones according to ongoing traffic or eventual disruptions."

Meta's quest to translate underserved languages is marking its first victory with the open source release of a language model able to decipher 202 languages. Named after Meta's No Language Left Behind initiative and dubbed NLLB-200, the model is the first able to translate so many languages, according to its makers, all with the goal to improve translation for languages overlooked by similar projects. "The vast majority of improvements made in machine translation in the last decades have been for high-resource languages," Meta researchers wrote in a paper [PDF]. "While machine translation continues to grow, the fruits it bears are unevenly distributed," they said. According to the announcement of NLLB-200, the model can translate 55 African languages "with high-quality results."

HCI researchers have been gradually shifting attention from individual users to communities when engaging in research, design, and system development. However, our field has yet to establish a cohesive, systematic understanding of the challenges, benefits, and commitments of community-collaborative approaches to research. We conducted a systematic review and thematic analysis of 47 computing research papers discussing participatory research with communities for the development of technological artifacts and systems, published over the last two decades. From this review, we identified seven themes associated with the evolution of a project: from establishing community partnerships to sustaining results. Our findings suggest that several tensions characterize these projects, many of which relate to the power and position of researchers, and the computing research environment, relative to community partners. We discuss the implications of our findings and offer methodological proposals to guide HCI, and computing research more broadly, towards practices that center communities.

Deep learning (DL) in general and Recurrent neural networks (RNNs) in particular have seen high success levels in sequence based applications. This paper pertains to RNNs for time series modelling and forecasting. We propose a novel RNN architecture capturing (stochastic) seasonal correlations intelligently while capable of accurate multi-step forecasting. It is motivated from the well-known encoder-decoder (ED) architecture and multiplicative seasonal auto-regressive model. It incorporates multi-step (multi-target) learning even in the presence (or absence) of exogenous inputs. It can be employed on single or multiple sequence data. For the multiple sequence case, we also propose a novel greedy recursive procedure to build (one or more) predictive models across sequences when per-sequence data is less. We demonstrate via extensive experiments the utility of our proposed architecture both in single sequence and multiple sequence scenarios.