Yifei Yin

Elvis Nava, Seijin Kobayashi, Yifei Yin et al. · eth-zurich, mit

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.

Yifei Yin, Chen Guo, Manuel Kaufmann et al.

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.

Pengcheng An, Jiawen Zhu, Zibo Zhang et al.

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.

Jiaao Yu, Shenwei Li, Mingjie Han et al.

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.

Pengcheng An, Ziqi Zhou, Qing Liu et al.

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.

Ying Zhou, Xuefeng Liang, Yu Gu et al.

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.