This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i.e., Kuaishou/Kwai Platform. The KVQ database is divided into three parts, including 2926 videos for training, 420 videos for validation, and 854 videos for testing. The purpose is to build new benchmarks and advance the development of S-UGC VQA. The competition had 200 participants and 13 teams submitted valid solutions for the final testing phase. The proposed solutions achieved state-of-the-art performances for S-UGC VQA. The project can be found at https://github.com/lixinustc/KVQChallenge-CVPR-NTIRE2024.
Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions. While none of existing approach thoroughly model such hierarchical inter-dependencies among AUs, this paper proposes to comprehensively model multi-scale AU-related dynamic and hierarchical spatio-temporal relationship among AUs for their occurrences recognition. Specifically, we first propose a novel multi-scale temporal differencing network with an adaptive weighting block to explicitly capture facial dynamics across frames at different spatial scales, which specifically considers the heterogeneity of range and magnitude in different AUs' activation. Then, a two-stage strategy is introduced to hierarchically model the relationship among AUs based on their spatial distribution (i.e., local and cross-region AU relationship modelling). Experimental results achieved on BP4D and DISFA show that our approach is the new state-of-the-art in the field of AU occurrence recognition. Our code is publicly available at https://github.com/CVI-SZU/MDHR.
The advancement of medical artificial intelligence (AI) has set the stage for the realization of conversational diagnosis, where AI systems mimic human doctors by engaging in dialogue with patients to deduce diagnoses. This study introduces an innovative approach using external planners augmented with large language models (LLMs) to develop a medical task-oriented dialogue system. This system comprises a policy module for information gathering, a LLM based module for natural language understanding and generation, addressing the limitations of previous AI systems in these areas. By emulating the two-phase decision-making process of doctors disease screening and differential diagnosis. we designed two distinct planners. The first focuses on collecting patient symptoms to identify potential diseases, while the second delves into specific inquiries to confirm or exclude these diseases. Utilizing reinforcement learning and active learning with LLMs, we trained these planners to navigate medical dialogues effectively. Our evaluation on the MIMIC-IV dataset demonstrated the system's capability to outperform existing models, indicating a significant step towards achieving automated conversational disease diagnostics and enhancing the precision and accessibility of medical diagnoses.
The detection of abusive language remains a long-standing challenge with the extensive use of social networks. The detection task of abusive language suffers from limited accuracy. We argue that the existing detection methods utilize the fine-tuning technique of the pre-trained language models (PLMs) to handle downstream tasks. Hence, these methods fail to stimulate the general knowledge of the PLMs. To address the problem, we propose a novel Deep Prompt Multi-task Network (DPMN) for abuse language detection. Specifically, DPMN first attempts to design two forms of deep prompt tuning and light prompt tuning for the PLMs. The effects of different prompt lengths, tuning strategies, and prompt initialization methods on detecting abusive language are studied. In addition, we propose a Task Head based on Bi-LSTM and FFN, which can be used as a short text classifier. Eventually, DPMN utilizes multi-task learning to improve detection metrics further. The multi-task network has the function of transferring effective knowledge. The proposed DPMN is evaluated against eight typical methods on three public datasets: OLID, SOLID, and AbuseAnalyzer. The experimental results show that our DPMN outperforms the state-of-the-art methods.
Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model augmentation) have been proposed. However, they show poor performances in attacking systems having different model genera from the surrogate model. In this paper, we propose a novel and generic attacking strategy, called Deformation-Constrained Warping Attack (DeCoWA), that can be effectively applied to cross model genus attack. Specifically, DeCoWA firstly augments input examples via an elastic deformation, namely Deformation-Constrained Warping (DeCoW), to obtain rich local details of the augmented input. To avoid severe distortion of global semantics led by random deformation, DeCoW further constrains the strength and direction of the warping transformation by a novel adaptive control strategy. Extensive experiments demonstrate that the transferable examples crafted by our DeCoWA on CNN surrogates can significantly hinder the performance of Transformers (and vice versa) on various tasks, including image classification, video action recognition, and audio recognition. Code is made available at https://github.com/LinQinLiang/DeCoWA.
In dyadic interactions, humans communicate their intentions and state of mind using verbal and non-verbal cues, where multiple different facial reactions might be appropriate in response to a specific speaker behaviour. Then, how to develop a machine learning (ML) model that can automatically generate multiple appropriate, diverse, realistic and synchronised human facial reactions from an previously unseen speaker behaviour is a challenging task. Following the successful organisation of the first REACT challenge (REACT 2023), this edition of the challenge (REACT 2024) employs a subset used by the previous challenge, which contains segmented 30-secs dyadic interaction clips originally recorded as part of the NOXI and RECOLA datasets, encouraging participants to develop and benchmark Machine Learning (ML) models that can generate multiple appropriate facial reactions (including facial image sequences and their attributes) given an input conversational partner's stimulus under various dyadic video conference scenarios. This paper presents: (i) the guidelines of the REACT 2024 challenge; (ii) the dataset utilized in the challenge; and (iii) the performance of the baseline systems on the two proposed sub-challenges: Offline Multiple Appropriate Facial Reaction Generation and Online Multiple Appropriate Facial Reaction Generation, respectively. The challenge baseline code is publicly available at https://github.com/reactmultimodalchallenge/baseline_react2024.
A customer service platform system with a core text semantic similarity (STS) task faces two urgent challenges: Firstly, one platform system needs to adapt to different domains of customers, i.e., different domains adaptation (DDA). Secondly, it is difficult for the model of the platform system to distinguish sentence pairs that are literally close but semantically different, i.e., hard negative samples. In this paper, we propose an incorporation external keywords matrices model (IEKM) to address these challenges. The model uses external tools or dictionaries to construct external matrices and fuses them to the self-attention layers of the Transformer structure through gating units, thus enabling flexible corrections to the model results. We evaluate the method on multiple datasets and the results show that our method has improved performance on all datasets. To demonstrate that our method can effectively solve all the above challenges, we conduct a flexible correction experiment, which results in an increase in the F1 value from 56.61 to 73.53. Our code will be publicly available.
Intelligent Reflecting Surface (IRS) utilizes low-cost, passive reflecting elements to enhance the passive beam gain, improve Wireless Energy Transfer (WET) efficiency, and enable its deployment for numerous Internet of Things (IoT) devices. However, the increasing number of IRS elements presents considerable channel estimation challenges. This is due to the lack of active Radio Frequency (RF) chains in an IRS, while pilot overhead becomes intolerable. To address this issue, we propose a Channel State Information (CSI)-free scheme that maximizes received energy in a specific direction and covers the entire space through phased beam rotation. Furthermore, we take into account the impact of an imperfect IRS and meticulously design the active precoder and IRS reflecting phase shift to mitigate its effects. Our proposed technique does not alter the existing IRS hardware architecture, allowing for easy implementation in the current system, and enabling access or removal of any Energy Receivers (ERs) without additional cost. Numerical results illustrate the efficacy of our CSI-free scheme in facilitating large-scale IRS without compromising performance due to excessive pilot overhead. Furthermore, our scheme outperforms the CSI-based counterpart in scenarios involving large-scale ERs, making it a promising solution in the era of IoT.
In the evolving landscape of neural network models, one prominent challenge stand out: the significant memory overheads associated with training expansive models. Addressing this challenge, this study delves deep into the Rotated Tensor Parallelism (RTP). RTP is an innovative approach that strategically focuses on memory deduplication in distributed training environments. It boasts of unique features like a customized communication primitive and the Flyweight Pattern initialization. Furthermore, RTP ensures a seamless overlap between partition computation and partition weight communication, optimizing the training process. Our empirical evaluations underscore RTP's efficiency, revealing that its memory consumption during distributed system training is remarkably close to the optimal - distributing the memory overhead of a single machine equitably among multiple machines. The experimental results demonstrate that RTP is capable of achieving comparable performance to Distributed Data Parallel while providing support for significantly larger models with near-linear scalability in terms of memory. Code of RTP is available at https://github.com/wdlctc/rtp.
This paper presents a reconfigurable intelligent sensing surface (RISS) that combines passive and active elements to achieve simultaneous reflection and direction of arrival (DOA) estimation tasks. By utilizing DOA information from the RISS instead of conventional channel estimation, the pilot overhead is reduced and the RISS becomes independent of the hybrid access point (HAP), enabling efficient operation. Specifically, the RISS autonomously estimates the DOA of uplink signals from single-antenna users and reflects them using the HAP's slowly varying DOA information. During downlink transmission, it updates the HAP's DOA information and designs the reflection phase of energy signals based on the latest user DOA information. The paper includes a comprehensive performance analysis, covering system design, protocol details, receiving performance, and RISS deployment suggestions. We derive a closed-form expression to analyze system performance under DOA errors, and calculate the statistical distribution of user received energy using the moment-matching technique. We provide a recommended transmit power to meet a specified outage probability and energy threshold. Numerical results demonstrate that the proposed system outperforms the conventional counterpart by 2.3 dB and 4.7 dB for Rician factors $\kappa_h=\kappa_G=1$ and $\kappa_h=\kappa_G=10$, respectively.