A Novel Approach to for Multimodal Emotion Recognition : Multimodal semantic information fusion

With the advancement of artificial intelligence and computer vision technologies, multimodal emotion recognition has become a prominent research topic. However, existing methods face challenges such as heterogeneous data fusion and the effective utilization of modality correlations. This paper proposes a novel multimodal emotion recognition approach, DeepMSI-MER, based on the integration of contrastive learning and visual sequence compression. The proposed method enhances cross-modal feature fusion through contrastive learning and reduces redundancy in the visual modality by leveraging visual sequence compression. Experimental results on two public datasets, IEMOCAP and MELD, demonstrate that DeepMSI-MER significantly improves the accuracy and robustness of emotion recognition, validating the effectiveness of multimodal feature fusion and the proposed approach.

Multi-Label Test-Time Adaptation with Bound Entropy Minimization

Mainstream test-time adaptation (TTA) techniques endeavor to mitigate distribution shifts via entropy minimization for multi-class classification, inherently increasing the probability of the most confident class. However, when encountering multi-label instances, the primary challenge stems from the varying number of labels per image, and prioritizing only the highest probability class inevitably undermines the adaptation of other positive labels. To address this issue, we investigate TTA within multi-label scenario (ML--TTA), developing Bound Entropy Minimization (BEM) objective to simultaneously increase the confidence of multiple top predicted labels. Specifically, to determine the number of labels for each augmented view, we retrieve a paired caption with yielded textual labels for that view. These labels are allocated to both the view and caption, called weak label set and strong label set with the same size k. Following this, the proposed BEM considers the highest top-k predicted labels from view and caption as a single entity, respectively, learning both view and caption prompts concurrently. By binding top-k predicted labels, BEM overcomes the limitation of vanilla entropy minimization, which exclusively optimizes the most confident class. Across the MSCOCO, VOC, and NUSWIDE multi-label datasets, our ML--TTA framework equipped with BEM exhibits superior performance compared to the latest SOTA methods, across various model architectures, prompt initialization, and varying label scenarios. The code is available at https://github.com/Jinx630/ML-TTA.

Versatile Volumetric Medical Image Coding for Human-Machine Vision

Neural image compression (NIC) has received considerable attention due to its significant advantages in feature representation and data optimization. However, most existing NIC methods for volumetric medical images focus solely on improving human-oriented perception. For these methods, data need to be decoded back to pixels for downstream machine learning analytics, which is a process that lowers the efficiency of diagnosis and treatment in modern digital healthcare scenarios. In this paper, we propose a Versatile Volumetric Medical Image Coding (VVMIC) framework for both human and machine vision, enabling various analytics of coded representations directly without decoding them into pixels. Considering the specific three-dimensional structure distinguished from natural frame images, a Versatile Volumetric Autoencoder (VVAE) module is crafted to learn the inter-slice latent representations to enhance the expressiveness of the current-slice latent representations, and to produce intermediate decoding features for downstream reconstruction and segmentation tasks. To further improve coding performance, a multi-dimensional context model is assembled by aggregating the inter-slice latent context with the spatial-channel context and the hierarchical hypercontext. Experimental results show that our VVMIC framework maintains high-quality image reconstruction for human vision while achieving accurate segmentation results for machine-vision tasks compared to a number of reported traditional and neural methods.

Federated Continual Learning for Edge-AI: A Comprehensive Survey

Edge-AI, the convergence of edge computing and artificial intelligence (AI), has become a promising paradigm that enables the deployment of advanced AI models at the network edge, close to users. In Edge-AI, federated continual learning (FCL) has emerged as an imperative framework, which fuses knowledge from different clients while preserving data privacy and retaining knowledge from previous tasks as it learns new ones. By so doing, FCL aims to ensure stable and reliable performance of learning models in dynamic and distributed environments. In this survey, we thoroughly review the state-of-the-art research and present the first comprehensive survey of FCL for Edge-AI. We categorize FCL methods based on three task characteristics: federated class continual learning, federated domain continual learning, and federated task continual learning. For each category, an in-depth investigation and review of the representative methods are provided, covering background, challenges, problem formalisation, solutions, and limitations. Besides, existing real-world applications empowered by FCL are reviewed, indicating the current progress and potential of FCL in diverse application domains. Furthermore, we discuss and highlight several prospective research directions of FCL such as algorithm-hardware co-design for FCL and FCL with foundation models, which could provide insights into the future development and practical deployment of FCL in the era of Edge-AI.

Seeing Through Pixel Motion: Learning Obstacle Avoidance from Optical Flow with One Camera

Optical flow captures the motion of pixels in an image sequence over time, providing information about movement, depth, and environmental structure. Flying insects utilize this information to navigate and avoid obstacles, allowing them to execute highly agile maneuvers even in complex environments. Despite its potential, autonomous flying robots have yet to fully leverage this motion information to achieve comparable levels of agility and robustness. Challenges of control from optical flow include extracting accurate optical flow at high speeds, handling noisy estimation, and ensuring robust performance in complex environments. To address these challenges, we propose a novel end-to-end system for quadrotor obstacle avoidance using monocular optical flow. We develop an efficient differentiable simulator coupled with a simplified quadrotor model, allowing our policy to be trained directly through first-order gradient optimization. Additionally, we introduce a central flow attention mechanism and an action-guided active sensing strategy that enhances the policy's focus on task-relevant optical flow observations to enable more responsive decision-making during flight. Our system is validated both in simulation and the real world using an FPV racing drone. Despite being trained in a simple environment in simulation, our system is validated both in simulation and the real world using an FPV racing drone. Despite being trained in a simple environment in simulation, our system demonstrates agile and robust flight in various unknown, cluttered environments in the real world at speeds of up to 6m/s.

CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models

Challenges in managing linguistic diversity and integrating various musical modalities are faced by current music information retrieval systems. These limitations reduce their effectiveness in a global, multimodal music environment. To address these issues, we introduce CLaMP 2, a system compatible with 101 languages that supports both ABC notation (a text-based musical notation format) and MIDI (Musical Instrument Digital Interface) for music information retrieval. CLaMP 2, pre-trained on 1.5 million ABC-MIDI-text triplets, includes a multilingual text encoder and a multimodal music encoder aligned via contrastive learning. By leveraging large language models, we obtain refined and consistent multilingual descriptions at scale, significantly reducing textual noise and balancing language distribution. Our experiments show that CLaMP 2 achieves state-of-the-art results in both multilingual semantic search and music classification across modalities, thus establishing a new standard for inclusive and global music information retrieval.

The Solution for the 5th GCAIAC Zero-shot Referring Expression Comprehension Challenge

This report presents a solution for the zero-shot referring expression comprehension task. Visual-language multimodal base models (such as CLIP, SAM) have gained significant attention in recent years as a cornerstone of mainstream research. One of the key applications of multimodal base models lies in their ability to generalize to zero-shot downstream tasks. Unlike traditional referring expression comprehension, zero-shot referring expression comprehension aims to apply pre-trained visual-language models directly to the task without specific training. Recent studies have enhanced the zero-shot performance of multimodal base models in referring expression comprehension tasks by introducing visual prompts. To address the zero-shot referring expression comprehension challenge, we introduced a combination of visual prompts and considered the influence of textual prompts, employing joint prediction tailored to the data characteristics. Ultimately, our approach achieved accuracy rates of 84.825 on the A leaderboard and 71.460 on the B leaderboard, securing the first position.

MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing

In the domain of symbolic music research, the progress of developing scalable systems has been notably hindered by the scarcity of available training data and the demand for models tailored to specific tasks. To address these issues, we propose MelodyT5, a novel unified framework that leverages an encoder-decoder architecture tailored for symbolic music processing in ABC notation. This framework challenges the conventional task-specific approach, considering various symbolic music tasks as score-to-score transformations. Consequently, it integrates seven melody-centric tasks, from generation to harmonization and segmentation, within a single model. Pre-trained on MelodyHub, a newly curated collection featuring over 261K unique melodies encoded in ABC notation and encompassing more than one million task instances, MelodyT5 demonstrates superior performance in symbolic music processing via multi-task transfer learning. Our findings highlight the efficacy of multi-task transfer learning in symbolic music processing, particularly for data-scarce tasks, challenging the prevailing task-specific paradigms and offering a comprehensive dataset and framework for future explorations in this domain.

A Subspace-Constrained Tyler's Estimator and its Applications to Structure from Motion

We present the subspace-constrained Tyler's estimator (STE) designed for recovering a low-dimensional subspace within a dataset that may be highly corrupted with outliers. STE is a fusion of the Tyler's M-estimator (TME) and a variant of the fast median subspace. Our theoretical analysis suggests that, under a common inlier-outlier model, STE can effectively recover the underlying subspace, even when it contains a smaller fraction of inliers relative to other methods in the field of robust subspace recovery. We apply STE in the context of Structure from Motion (SfM) in two ways: for robust estimation of the fundamental matrix and for the removal of outlying cameras, enhancing the robustness of the SfM pipeline. Numerical experiments confirm the state-of-the-art performance of our method in these applications. This research makes significant contributions to the field of robust subspace recovery, particularly in the context of computer vision and 3D reconstruction.

Theoretical Guarantees for the Subspace-Constrained Tyler's Estimator

This work analyzes the subspace-constrained Tyler's estimator (STE) designed for recovering a low-dimensional subspace within a dataset that may be highly corrupted with outliers. It assumes a weak inlier-outlier model and allows the fraction of inliers to be smaller than a fraction that leads to computational hardness of the robust subspace recovery problem. It shows that in this setting, if the initialization of STE, which is an iterative algorithm, satisfies a certain condition, then STE can effectively recover the underlying subspace. It further shows that under the generalized haystack model, STE initialized by the Tyler's M-estimator (TME), can recover the subspace when the fraction of iniliers is too small for TME to handle.