Context-Aware Deep Learning for Multi Modal Depression Detection

In this study, we focus on automated approaches to detect depression from clinical interviews using multi-modal machine learning (ML). Our approach differentiates from other successful ML methods such as context-aware analysis through feature engineering and end-to-end deep neural networks for depression detection utilizing the Distress Analysis Interview Corpus. We propose a novel method that incorporates: (1) pre-trained Transformer combined with data augmentation based on topic modelling for textual data; and (2) deep 1D convolutional neural network (CNN) for acoustic feature modeling. The simulation results demonstrate the effectiveness of the proposed method for training multi-modal deep learning models. Our deep 1D CNN and Transformer models achieved state-of-the-art performance for audio and text modalities respectively. Combining them in a multi-modal framework also outperforms state-of-the-art for the combined setting. Code available at https://github.com/genandlam/multi-modal-depression-detection

VQA$^2$:Visual Question Answering for Video Quality Assessment

The advent and proliferation of large multi-modal models (LMMs) have introduced a new paradigm to video-related computer vision fields, including training and inference methods based on visual question answering (VQA). These methods enable models to handle multiple downstream tasks robustly. Video Quality Assessment (VQA), a classic field in low-level visual quality evaluation, originally focused on quantitative video quality scoring. However, driven by advances in LMMs, it is now evolving towards more comprehensive visual quality understanding tasks. Visual question answering has significantly improved low-level visual evaluation within the image domain recently. However, related work is almost nonexistent in the video domain, leaving substantial room for improvement. To address this gap, we introduce the VQA2 Instruction Dataset the first visual question answering instruction dataset entirely focuses on video quality assessment, and based on it, we propose the VQA2 series models The VQA2 Instruction Dataset consists of three stages and covers various video types, containing 157,735 instruction question-answer pairs, including both manually annotated and synthetic data. We conduct extensive experiments on both video quality scoring and video quality understanding tasks. Results demonstrate that the VQA2 series models achieve state-of-the-art (SOTA) performance in quality scoring tasks, and their performance in visual quality question answering surpasses the renowned GPT-4o. Additionally, our final model, the VQA2-Assistant, performs well across both scoring and question-answering tasks, validating its versatility.

R-Bench: Are your Large Multimodal Model Robust to Real-world Corruptions?

The outstanding performance of Large Multimodal Models (LMMs) has made them widely applied in vision-related tasks. However, various corruptions in the real world mean that images will not be as ideal as in simulations, presenting significant challenges for the practical application of LMMs. To address this issue, we introduce R-Bench, a benchmark focused on the **Real-world Robustness of LMMs**. Specifically, we: (a) model the complete link from user capture to LMMs reception, comprising 33 corruption dimensions, including 7 steps according to the corruption sequence, and 7 groups based on low-level attributes; (b) collect reference/distorted image dataset before/after corruption, including 2,970 question-answer pairs with human labeling; (c) propose comprehensive evaluation for absolute/relative robustness and benchmark 20 mainstream LMMs. Results show that while LMMs can correctly handle the original reference images, their performance is not stable when faced with distorted images, and there is a significant gap in robustness compared to the human visual system. We hope that R-Bench will inspire improving the robustness of LMMs, **extending them from experimental simulations to the real-world application**. Check https://q-future.github.io/R-Bench for details.

Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs

With the rising interest in research on Large Multi-modal Models (LMMs) for video understanding, many studies have emphasized general video comprehension capabilities, neglecting the systematic exploration into video quality understanding. To address this oversight, we introduce Q-Bench-Video in this paper, a new benchmark specifically designed to evaluate LMMs' proficiency in discerning video quality. a) To ensure video source diversity, Q-Bench-Video encompasses videos from natural scenes, AI-generated Content (AIGC), and Computer Graphics (CG). b) Building on the traditional multiple-choice questions format with the Yes-or-No and What-How categories, we include Open-ended questions to better evaluate complex scenarios. Additionally, we incorporate the video pair quality comparison question to enhance comprehensiveness. c) Beyond the traditional Technical, Aesthetic, and Temporal distortions, we have expanded our evaluation aspects to include the dimension of AIGC distortions, which addresses the increasing demand for video generation. Finally, we collect a total of 2,378 question-answer pairs and test them on 12 open-source & 5 proprietary LMMs. Our findings indicate that while LMMs have a foundational understanding of video quality, their performance remains incomplete and imprecise, with a notable discrepancy compared to human performance. Through Q-Bench-Video, we seek to catalyze community interest, stimulate further research, and unlock the untapped potential of LMMs to close the gap in video quality understanding.

Explore the Hallucination on Low-level Perception for MLLMs

The rapid development of Multi-modality Large Language Models (MLLMs) has significantly influenced various aspects of industry and daily life, showcasing impressive capabilities in visual perception and understanding. However, these models also exhibit hallucinations, which limit their reliability as AI systems, especially in tasks involving low-level visual perception and understanding. We believe that hallucinations stem from a lack of explicit self-awareness in these models, which directly impacts their overall performance. In this paper, we aim to define and evaluate the self-awareness of MLLMs in low-level visual perception and understanding tasks. To this end, we present QL-Bench, a benchmark settings to simulate human responses to low-level vision, investigating self-awareness in low-level visual perception through visual question answering related to low-level attributes such as clarity and lighting. Specifically, we construct the LLSAVisionQA dataset, comprising 2,990 single images and 1,999 image pairs, each accompanied by an open-ended question about its low-level features. Through the evaluation of 15 MLLMs, we demonstrate that while some models exhibit robust low-level visual capabilities, their self-awareness remains relatively underdeveloped. Notably, for the same model, simpler questions are often answered more accurately than complex ones. However, self-awareness appears to improve when addressing more challenging questions. We hope that our benchmark will motivate further research, particularly focused on enhancing the self-awareness of MLLMs in tasks involving low-level visual perception and understanding.

MRSE: An Efficient Multi-modality Retrieval System for Large Scale E-commerce

Providing high-quality item recall for text queries is crucial in large-scale e-commerce search systems. Current Embedding-based Retrieval Systems (ERS) embed queries and items into a shared low-dimensional space, but uni-modality ERS rely too heavily on textual features, making them unreliable in complex contexts. While multi-modality ERS incorporate various data sources, they often overlook individual preferences for different modalities, leading to suboptimal results. To address these issues, we propose MRSE, a Multi-modality Retrieval System that integrates text, item images, and user preferences through lightweight mixture-of-expert (LMoE) modules to better align features across and within modalities. MRSE also builds user profiles at a multi-modality level and introduces a novel hybrid loss function that enhances consistency and robustness using hard negative sampling. Experiments on a large-scale dataset from Shopee and online A/B testing show that MRSE achieves an 18.9% improvement in offline relevance and a 3.7% gain in online core metrics compared to Shopee's state-of-the-art uni-modality system.

UNQA: Unified No-Reference Quality Assessment for Audio, Image, Video, and Audio-Visual Content

As multimedia data flourishes on the Internet, quality assessment (QA) of multimedia data becomes paramount for digital media applications. Since multimedia data includes multiple modalities including audio, image, video, and audio-visual (A/V) content, researchers have developed a range of QA methods to evaluate the quality of different modality data. While they exclusively focus on addressing the single modality QA issues, a unified QA model that can handle diverse media across multiple modalities is still missing, whereas the latter can better resemble human perception behaviour and also have a wider range of applications. In this paper, we propose the Unified No-reference Quality Assessment model (UNQA) for audio, image, video, and A/V content, which tries to train a single QA model across different media modalities. To tackle the issue of inconsistent quality scales among different QA databases, we develop a multi-modality strategy to jointly train UNQA on multiple QA databases. Based on the input modality, UNQA selectively extracts the spatial features, motion features, and audio features, and calculates a final quality score via the four corresponding modality regression modules. Compared with existing QA methods, UNQA has two advantages: 1) the multi-modality training strategy makes the QA model learn more general and robust quality-aware feature representation as evidenced by the superior performance of UNQA compared to state-of-the-art QA methods. 2) UNQA reduces the number of models required to assess multimedia data across different modalities. and is friendly to deploy to practical applications.

Q-Ground: Image Quality Grounding with Large Multi-modality Models

Recent advances of large multi-modality models (LMM) have greatly improved the ability of image quality assessment (IQA) method to evaluate and explain the quality of visual content. However, these advancements are mostly focused on overall quality assessment, and the detailed examination of local quality, which is crucial for comprehensive visual understanding, is still largely unexplored. In this work, we introduce Q-Ground, the first framework aimed at tackling fine-scale visual quality grounding by combining large multi-modality models with detailed visual quality analysis. Central to our contribution is the introduction of the QGround-100K dataset, a novel resource containing 100k triplets of (image, quality text, distortion segmentation) to facilitate deep investigations into visual quality. The dataset comprises two parts: one with human-labeled annotations for accurate quality assessment, and another labeled automatically by LMMs such as GPT4V, which helps improve the robustness of model training while also reducing the costs of data collection. With the QGround-100K dataset, we propose a LMM-based method equipped with multi-scale feature learning to learn models capable of performing both image quality answering and distortion segmentation based on text prompts. This dual-capability approach not only refines the model's understanding of region-aware image quality but also enables it to interactively respond to complex, text-based queries about image quality and specific distortions. Q-Ground takes a step towards sophisticated visual quality analysis in a finer scale, establishing a new benchmark for future research in the area. Codes and dataset are available at https://github.com/Q-Future/Q-Ground.

DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection

Applying deep neural networks to 3D point cloud processing has attracted increasing attention due to its advanced performance in many areas, such as AR/VR, autonomous driving, and robotics. However, as neural network models and 3D point clouds expand in size, it becomes a crucial challenge to reduce the computational and memory overhead to meet latency and energy constraints in real-world applications. Although existing approaches have proposed to reduce both computational cost and memory footprint, most of them only address the spatial redundancy in inputs, i.e. removing the redundancy of background points in 3D data. In this paper, we propose a novel post-training weight pruning scheme for 3D object detection that is (1) orthogonal to all existing point cloud sparsifying methods, which determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence (detection distortion); and (2) a universal plug-and-play pruning framework that works with arbitrary 3D detection model. This framework aims to minimize detection distortion of network output to maximally maintain detection precision, by identifying layer-wise sparsity based on second-order Taylor approximation of the distortion. Albeit utilizing second-order information, we introduced a lightweight scheme to efficiently acquire Hessian information, and subsequently perform dynamic programming to solve the layer-wise sparsity. Extensive experiments on KITTI, Nuscenes and ONCE datasets demonstrate that our approach is able to maintain and even boost the detection precision on pruned model under noticeable computation reduction (FLOPs). Noticeably, we achieve over 3.89x, 3.72x FLOPs reduction on CenterPoint and PVRCNN model, respectively, without mAP decrease, significantly improving the state-of-the-art.

LPViT: Low-Power Semi-structured Pruning for Vision Transformers

Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their resource-intensive nature, leading to increased memory footprint, computation complexity, and power consumption. To democratize this high-performance technology and make it more environmentally friendly, it is essential to compress ViT models, reducing their resource requirements while maintaining high performance. In this paper, we introduce a new block-structured pruning to address the resource-intensive issue for ViTs, offering a balanced trade-off between accuracy and hardware acceleration. Unlike unstructured pruning or channel-wise structured pruning, block pruning leverages the block-wise structure of linear layers, resulting in more efficient matrix multiplications. To optimize this pruning scheme, our paper proposes a novel hardware-aware learning objective that simultaneously maximizes speedup and minimizes power consumption during inference, tailored to the block sparsity structure. This objective eliminates the need for empirical look-up tables and focuses solely on reducing parametrized layer connections. Moreover, our paper provides a lightweight algorithm to achieve post-training pruning for ViTs, utilizing second-order Taylor approximation and empirical optimization to solve the proposed hardware-aware objective. Extensive experiments on ImageNet are conducted across various ViT architectures, including DeiT-B and DeiT-S, demonstrating competitive performance with other pruning methods and achieving a remarkable balance between accuracy preservation and power savings. Especially, we achieve up to 3.93x and 1.79x speedups on dedicated hardware and GPUs respectively for DeiT-B, and also observe an inference power reduction by 1.4x on real-world GPUs.