arXiv subjects

Yifei Yin

Publications and source records attributed to Yifei Yin.

8 recordsLinked to original sources

arXiv2026

Physics-Driven Semantic Scattering Structure Understanding of Aircraft Target in SAR Images

Synthetic aperture radar (SAR) has become indispensable for target interpretation owing to its all-day and all-weather observation capability. In SAR target interpretation, electromagnetic scattering information provides a physically grounded cue beyond visual texture and has been widely exploited for target interpretation. However, existing methods remain dominated by local scattering center representations. Such unordered and component-agnostic representations are highly unstable for aircraft targets. As a result, physically existing components with weak scattering responses are often missed, resulting in the incomplete reconstructed topology structure. To address this limitation, we establish Semantic Scattering Structure Understanding as a new paradigm for SAR aircraft interpretation. Semantic scattering keypoints are defined to associate local electromagnetic responses with physically meaningful aircraft components, while visibility-aware attributes are introduced to retain weakly observable yet physically existed components. The keypoints are further organized into a stable semantic scattering structure. Build upon this, we propose S3U-SAR, a physics-driven framework to localize semantic scattering keypoints and construct the complete representation constrained by multi-dimensional physical priors containing scattering heterogeneity, rigid-body topology, speckle uncertainty. A confidence-gated joint supervision strategy is further introduced to alleviate optimization conflicts. We construct KP-SAR-Aircraft-1.0, the first fine-grained benchmark for semantic scattering structure understanding. Extensive experiments demonstrate that S3U-SAR achieves the best performance compared with baselines. Cross-category and cross-dataset evaluations further verify its robustness and transferability.

eess.IV↗

arXiv2025

Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real world multimodal scenarios, most notably, vision language tasks, due to a heavy focus on single modal language settings. While efforts to transplant reinforcement learning techniques from NLP to VLMs have emerged, these approaches often remain confined to perception centric tasks or reduce images to textual summaries, failing to fully exploit visual context and commonsense knowledge, ultimately constraining the generalization of reasoning capabilities across diverse multimodal environments. To address this limitation, we introduce a novel fine tuning task, Masked Prediction via Context and Commonsense, which forces models to integrate visual context and commonsense reasoning by reconstructing semantically meaningful content from occluded images, thereby laying the foundation for generalized reasoning. To systematically evaluate the model performance in generalized reasoning, we developed a specialized evaluation benchmark, MPCC Eval, and employed various fine tuning strategies to guide reasoning. Among these, we introduced an innovative training method, Reinforcement Fine tuning with Prior Sampling, which not only enhances model performance but also improves its generalized reasoning capabilities in OOD and cross task scenarios.

cs.CV↗

arXiv2025

Purely Speckled Intensity Images Need for SAR Despeckling with SDS-SAR

Speckle noise is generated along with the SAR imaging mechanism and degrades the quality of SAR images, leading to difficult interpretation. Hence, despeckling is an indispensable step in SAR pre-processing. Fortunately, supervised learning (SL) has proven to be a progressive method for SAR image despeckling. SL methods necessitate the availability of both original SAR images and their speckle-free counterparts during training, whilst speckle-free SAR images do not exist in the real world. Even though there are several substitutes for speckle-free images, the domain gap leads to poor performance and adaptability. Self-supervision provides an approach to training without clean reference. However, most self-supervised methods impose high demands on speckle modeling or specific data, limiting their practicality in real-world applications. To address these challenges, we propose a Self-supervised Despeckling Strategy for SAR images (SDS-SAR) that relies solely on speckled intensity data for training. Firstly, the theoretical feasibility of SAR image despeckling without speckle-free images is established. A self-supervised despeckling criteria suitable for all SAR images is proposed. Subsequently, a Random-Aware sub-SAMpler with Projection correLation Estimation (RA-SAMPLE) is put forth. Mutually independent training pairs can be derived from actual SAR intensity images. Furthermore, a multi-feature loss function is introduced, consisting of a despeckling term, a regularization term, and a perception term. The performance of speckle suppression and texture preservation is well-balanced. Experiments reveal that the proposed method performs on par with supervised approaches on synthetic data and outperforms them on actual data.

eess.IV↗

arXiv2024

EmoWear: Exploring Emotional Teasers for Voice Message Interaction on Smartwatches

Voice messages, by nature, prevent users from gauging the emotional tone without fully diving into the audio content. This hinders the shared emotional experience at the pre-retrieval stage. Research scarcely explored "Emotional Teasers"-pre-retrieval cues offering a glimpse into an awaiting message's emotional tone without disclosing its content. We introduce EmoWear, a smartwatch voice messaging system enabling users to apply 30 animation teasers on message bubbles to reflect emotions. EmoWear eases senders' choice by prioritizing emotions based on semantic and acoustic processing. EmoWear was evaluated in comparison with a mirroring system using color-coded message bubbles as emotional cues (N=24). Results showed EmoWear significantly enhanced emotional communication experience in both receiving and sending messages. The animated teasers were considered intuitive and valued for diverse expressions. Desirable interaction qualities and practical implications are distilled for future design. We thereby contribute both a novel system and empirical knowledge concerning emotional teasers for voice messaging.

cs.HC↗

arXiv2023

Hi4D: 4D Instance Segmentation of Close Human Interaction

We propose Hi4D, a method and dataset for the automatic analysis of physically close human-human interaction under prolonged contact. Robustly disentangling several in-contact subjects is a challenging task due to occlusions and complex shapes. Hence, existing multi-view systems typically fuse 3D surfaces of close subjects into a single, connected mesh. To address this issue we leverage i) individually fitted neural implicit avatars; ii) an alternating optimization scheme that refines pose and surface through periods of close proximity; and iii) thus segment the fused raw scans into individual instances. From these instances we compile Hi4D dataset of 4D textured scans of 20 subject pairs, 100 sequences, and a total of more than 11K frames. Hi4D contains rich interaction-centric annotations in 2D and 3D alongside accurately registered parametric body models. We define varied human pose and shape estimation tasks on this dataset and provide results from state-of-the-art methods on these benchmarks.

cs.CV↗

arXiv2023

Meta-Learning via Classifier(-free) Diffusion Guidance

We introduce meta-learning algorithms that perform zero-shot weight-space adaptation of neural network models to unseen tasks. Our methods repurpose the popular generative image synthesis techniques of natural language guidance and diffusion models to generate neural network weights adapted for tasks. We first train an unconditional generative hypernetwork model to produce neural network weights; then we train a second "guidance" model that, given a natural language task description, traverses the hypernetwork latent space to find high-performance task-adapted weights in a zero-shot manner. We explore two alternative approaches for latent space guidance: "HyperCLIP"-based classifier guidance and a conditional Hypernetwork Latent Diffusion Model ("HyperLDM"), which we show to benefit from the classifier-free guidance technique common in image generation. Finally, we demonstrate that our approaches outperform existing multi-task and meta-learning methods in a series of zero-shot learning experiments on our Meta-VQA dataset.

cs.LG↗

arXiv2021

VibEmoji: Exploring User-authoring Multi-modal Emoticons in Social Communication

Emoticons are indispensable in online communications. With users' growing needs for more customized and expressive emoticons, recent messaging applications begin to support (limited) multi-modal emoticons: e.g., enhancing emoticons with animations or vibrotactile feedback. However, little empirical knowledge has been accumulated concerning how people create, share and experience multi-modal emoticons in everyday communication, and how to better support them through design. To tackle this, we developed VibEmoji, a user-authoring multi-modal emoticon interface for mobile messaging. Extending existing designs, VibEmoji grants users greater flexibility to combine various emoticons, vibrations, and animations on-the-fly, and offers non-aggressive recommendations based on these components' emotional relevance. Using VibEmoji as a probe, we conducted a four-week field study with 20 participants, to gain new understandings from in-the-wild usage and experience, and extract implications for design. We thereby contribute both a novel system and various insights for supporting users' creation and communication of multi-modal emoticons.

cs.HC↗

arXiv2020

Multi-Classifier Interactive Learning for Ambiguous Speech Emotion Recognition

In recent years, speech emotion recognition technology is of great significance in industrial applications such as call centers, social robots and health care. The combination of speech recognition and speech emotion recognition can improve the feedback efficiency and the quality of service. Thus, the speech emotion recognition has been attracted much attention in both industry and academic. Since emotions existing in an entire utterance may have varied probabilities, speech emotion is likely to be ambiguous, which poses great challenges to recognition tasks. However, previous studies commonly assigned a single-label or multi-label to each utterance in certain. Therefore, their algorithms result in low accuracies because of the inappropriate representation. Inspired by the optimally interacting theory, we address the ambiguous speech emotions by proposing a novel multi-classifier interactive learning (MCIL) method. In MCIL, multiple different classifiers first mimic several individuals, who have inconsistent cognitions of ambiguous emotions, and construct new ambiguous labels (the emotion probability distribution). Then, they are retrained with the new labels to interact with their cognitions. This procedure enables each classifier to learn better representations of ambiguous data from others, and further improves the recognition ability. The experiments on three benchmark corpora (MAS, IEMOCAP, and FAU-AIBO) demonstrate that MCIL does not only improve each classifier's performance, but also raises their recognition consistency from moderate to substantial.

cs.AI↗