Peng Zhang

Fangye Wang, Yingxu Wang, Dongsheng Li et al.

Many Click-Through Rate (CTR) prediction works focused on designing advanced architectures to model complex feature interactions but neglected the importance of feature representation learning, e.g., adopting a plain embedding layer for each feature, which results in sub-optimal feature representations and thus inferior CTR prediction performance. For instance, low frequency features, which account for the majority of features in many CTR tasks, are less considered in standard supervised learning settings, leading to sub-optimal feature representations. In this paper, we introduce self-supervised learning to produce high-quality feature representations directly and propose a model-agnostic Contrastive Learning for CTR (CL4CTR) framework consisting of three self-supervised learning signals to regularize the feature representation learning: contrastive loss, feature alignment, and field uniformity. The contrastive module first constructs positive feature pairs by data augmentation and then minimizes the distance between the representations of each positive feature pair by the contrastive loss. The feature alignment constraint forces the representations of features from the same field to be close, and the field uniformity constraint forces the representations of features from different fields to be distant. Extensive experiments verify that CL4CTR achieves the best performance on four datasets and has excellent effectiveness and compatibility with various representative baselines.

Li Hu, Guangyuan Wang, Zhen Shen et al.

Recent character image animation methods based on diffusion models, such as Animate Anyone, have made significant progress in generating consistent and generalizable character animations. However, these approaches fail to produce reasonable associations between characters and their environments. To address this limitation, we introduce Animate Anyone 2, aiming to animate characters with environment affordance. Beyond extracting motion signals from source video, we additionally capture environmental representations as conditional inputs. The environment is formulated as the region with the exclusion of characters and our model generates characters to populate these regions while maintaining coherence with the environmental context. We propose a shape-agnostic mask strategy that more effectively characterizes the relationship between character and environment. Furthermore, to enhance the fidelity of object interactions, we leverage an object guider to extract features of interacting objects and employ spatial blending for feature injection. We also introduce a pose modulation strategy that enables the model to handle more diverse motion patterns. Experimental results demonstrate the superior performance of the proposed method.

Yaqiong Li, Peng Zhang, Hansu Gu et al.

Although there have been automated approaches and tools supporting toxicity censorship for social posts, most of them focus on detection. Toxicity censorship is a complex process, wherein detection is just an initial task and a user can have further needs such as rationale understanding and content modification. For this problem, we conduct a needfinding study to investigate people's diverse needs in toxicity censorship and then build a ChatGPT-based censorship tool named DeMod accordingly. DeMod is equipped with the features of explainable Detection and personalized Modification, providing fine-grained detection results, detailed explanations, and personalized modification suggestions. We also implemented the tool and recruited 35 Weibo users for evaluation. The results suggest DeMod's multiple strengths like the richness of functionality, the accuracy of censorship, and ease of use. Based on the findings, we further propose several insights into the design of content censorship systems.

Zhongjian Wang, Peng Zhang, Jinwei Qi et al.

Although significant progress has been made in audio-driven talking head generation, text-driven methods remain underexplored. In this work, we present OmniTalker, a unified framework that jointly generates synchronized talking audio-video content from input text while emulating the speaking and facial movement styles of the target identity, including speech characteristics, head motion, and facial dynamics. Our framework adopts a dual-branch diffusion transformer (DiT) architecture, with one branch dedicated to audio generation and the other to video synthesis. At the shallow layers, cross-modal fusion modules are introduced to integrate information between the two modalities. In deeper layers, each modality is processed independently, with the generated audio decoded by a vocoder and the video rendered using a GAN-based high-quality visual renderer. Leveraging the in-context learning capability of DiT through a masked-infilling strategy, our model can simultaneously capture both audio and visual styles without requiring explicit style extraction modules. Thanks to the efficiency of the DiT backbone and the optimized visual renderer, OmniTalker achieves real-time inference at 25 FPS. To the best of our knowledge, OmniTalker is the first one-shot framework capable of jointly modeling speech and facial styles in real time. Extensive experiments demonstrate its superiority over existing methods in terms of generation quality, particularly in preserving style consistency and ensuring precise audio-video synchronization, all while maintaining efficient inference.

Xianghua Ding, Shuhan Wei, Xinning Gui et al.

In today's fast-paced world, stress has become a growing health concern. While more automatic stress tracking technologies have recently become available on wearable or mobile devices, there is still a limited understanding of how they are actually used in everyday life. This paper presents an empirical study of automatic stress-tracking technologies in use in China, based on semi-structured interviews with 17 users. The study highlights three challenges of stress-tracking data engagement that prevent effective technology usage: the lack of immediate awareness, the lack of pre-required knowledge, and the lack of corresponding communal support. Drawing on the stress-tracking practices uncovered in the study, we bring these issues to the fore, and unpack assumptions embedded in related works on self-tracking and how data engagement is approached. We end by calling for a reconsideration of data engagement as part of self-tracking practices with technologies rather than simply looking at the user interface.