SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis

Achieving high synchronization in the synthesis of realistic, speech-driven talking head videos presents a significant challenge. Traditional Generative Adversarial Networks (GAN) struggle to maintain consistent facial identity, while Neural Radiance Fields (NeRF) methods, although they can address this issue, often produce mismatched lip movements, inadequate facial expressions, and unstable head poses. A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses. The absence of these synchronizations is a fundamental flaw, leading to unrealistic and artificial outcomes. To address the critical issue of synchronization, identified as the "devil" in creating realistic talking heads, we introduce SyncTalk. This NeRF-based method effectively maintains subject identity, enhancing synchronization and realism in talking head synthesis. SyncTalk employs a Face-Sync Controller to align lip movements with speech and innovatively uses a 3D facial blendshape model to capture accurate facial expressions. Our Head-Sync Stabilizer optimizes head poses, achieving more natural head movements. The Portrait-Sync Generator restores hair details and blends the generated head with the torso for a seamless visual experience. Extensive experiments and user studies demonstrate that SyncTalk outperforms state-of-the-art methods in synchronization and realism. We recommend watching the supplementary video: https://ziqiaopeng.github.io/synctalk

Fast Estimations of Hitting Time of Elitist Evolutionary Algorithms from Fitness Levels

The fitness level method is an easy-to-use tool for estimating the hitting time of elitist EAs. Recently, general linear lower and upper bounds from fitness levels have been constructed. However, the construction of these bounds requires recursive computation, which makes them difficult to use in practice. We address this shortcoming with a new directed graph (digraph) method that does not require recursive computation and significantly simplifies the calculation of coefficients in linear bounds. In this method, an EA is modeled as a Markov chain on a digraph. Lower and upper bounds are directly calculated using conditional transition probabilities on the digraph. This digraph method provides straightforward and explicit expressions of lower and upper time bound for elitist EAs. In particular, it can be used to derive tight lower bound on both fitness landscapes without and with shortcuts. This is demonstrated through four examples: the (1+1) EA on OneMax, FullyDeceptive, TwoMax1 and Deceptive. Our work extends the fitness level method from addressing simple fitness functions without shortcuts to more realistic functions with shortcuts.

BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval

Dance and music are closely related forms of expression, with mutual retrieval between dance videos and music being a fundamental task in various fields like education, art, and sports. However, existing methods often suffer from unnatural generation effects or fail to fully explore the correlation between music and dance. To overcome these challenges, we propose BeatDance, a novel beat-based model-agnostic contrastive learning framework. BeatDance incorporates a Beat-Aware Music-Dance InfoExtractor, a Trans-Temporal Beat Blender, and a Beat-Enhanced Hubness Reducer to improve dance-music retrieval performance by utilizing the alignment between music beats and dance movements. We also introduce the Music-Dance (MD) dataset, a large-scale collection of over 10,000 music-dance video pairs for training and testing. Experimental results on the MD dataset demonstrate the superiority of our method over existing baselines, achieving state-of-the-art performance. The code and dataset will be made public available upon acceptance.

STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generation

Scene Graph Generation is a critical enabler of environmental comprehension for autonomous robotic systems. Most of existing methods, however, are often thwarted by the intricate dynamics of background complexity, which limits their ability to fully decode the inherent topological information of the environment. Additionally, the wealth of contextual information encapsulated within depth cues is often left untapped, rendering existing approaches less effective. To address these shortcomings, we present STDG, an avant-garde Depth-Guided One-Stage Scene Graph Generation methodology. The innovative architecture of STDG is a triad of custom-built modules: The Depth Guided HHA Representation Generation Module, the Depth Guided Semi-Teaching Network Learning Module, and the Depth Guided Scene Graph Generation Module. This trifecta of modules synergistically harnesses depth information, covering all aspects from depth signal generation and depth feature utilization, to the final scene graph prediction. Importantly, this is achieved without imposing additional computational burden during the inference phase. Experimental results confirm that our method significantly enhances the performance of one-stage scene graph generation baselines.

Drift Analysis with Fitness Levels for Elitist Evolutionary Algorithms

The fitness level method is a popular tool for analyzing the computation time of elitist evolutionary algorithms. Its idea is to divide the search space into multiple fitness levels and estimate lower and upper bounds on the computation time using transition probabilities between fitness levels. However, the lower bound generated from this method is often not tight. To improve the lower bound, this paper rigorously studies an open question about the fitness level method: what are the tightest lower and upper time bounds that can be constructed based on fitness levels? To answer this question, drift analysis with fitness levels is developed, and the tightest bound problem is formulated as a constrained multi-objective optimization problem subject to fitness level constraints. The tightest metric bounds from fitness levels are constructed and proven for the first time. Then the metric bounds are converted into linear bounds, where existing linear bounds are special cases. This paper establishes a general framework that can cover various linear bounds from trivial to best coefficients. It is generic and promising, as it can be used not only to draw the same bounds as existing ones, but also to draw tighter bounds, especially on fitness landscapes where shortcuts exist. This is demonstrated in the case study of the (1+1) EA maximizing the TwoPath function.

SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces

Speech-driven 3D face animation technique, extending its applications to various multimedia fields. Previous research has generated promising realistic lip movements and facial expressions from audio signals. However, traditional regression models solely driven by data face several essential problems, such as difficulties in accessing precise labels and domain gaps between different modalities, leading to unsatisfactory results lacking precision and coherence. To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces. The framework constructs a network system consisting of three modules: facial animator, speech recognizer, and lip-reading interpreter. The core of SelfTalk is a commutative training diagram that facilitates compatible features exchange among audio, text, and lip shape, enabling our models to learn the intricate connection between these factors. The proposed framework leverages the knowledge learned from the lip-reading interpreter to generate more plausible lip shapes. Extensive experiments and user studies demonstrate that our proposed approach achieves state-of-the-art performance both qualitatively and quantitatively. We recommend watching the supplementary video.

Backdoor Attacks with Input-unique Triggers in NLP

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems. Existing backdoor attacking systems face two severe issues:firstly, most backdoor triggers follow a uniform and usually input-independent pattern, e.g., insertion of specific trigger words, synonym replacement. This significantly hinders the stealthiness of the attacking model, leading the trained backdoor model being easily identified as malicious by model probes. Secondly, trigger-inserted poisoned sentences are usually disfluent, ungrammatical, or even change the semantic meaning from the original sentence, making them being easily filtered in the pre-processing stage. To resolve these two issues, in this paper, we propose an input-unique backdoor attack(NURA), where we generate backdoor triggers unique to inputs. IDBA generates context-related triggers by continuing writing the input with a language model like GPT2. The generated sentence is used as the backdoor trigger. This strategy not only creates input-unique backdoor triggers, but also preserves the semantics of the original input, simultaneously resolving the two issues above. Experimental results show that the IDBA attack is effective for attack and difficult to defend: it achieves high attack success rate across all the widely applied benchmarks, while is immune to existing defending methods. In addition, it is able to generate fluent, grammatical, and diverse backdoor inputs, which can hardly be recognized through human inspection.

EmoTalk: Speech-driven emotional disentanglement for 3D face animation

Speech-driven 3D face animation aims to generate realistic facial expressions that match the speech content and emotion. However, existing methods often neglect emotional facial expressions or fail to disentangle them from speech content. To address this issue, this paper proposes an end-to-end neural network to disentangle different emotions in speech so as to generate rich 3D facial expressions. Specifically, we introduce the emotion disentangling encoder (EDE) to disentangle the emotion and content in the speech by cross-reconstructed speech signals with different emotion labels. Then an emotion-guided feature fusion decoder is employed to generate a 3D talking face with enhanced emotion. The decoder is driven by the disentangled identity, emotional, and content embeddings so as to generate controllable personal and emotional styles. Finally, considering the scarcity of the 3D emotional talking face data, we resort to the supervision of facial blendshapes, which enables the reconstruction of plausible 3D faces from 2D emotional data, and contribute a large-scale 3D emotional talking face dataset (3D-ETF) to train the network. Our experiments and user studies demonstrate that our approach outperforms state-of-the-art methods and exhibits more diverse facial movements. We recommend watching the supplementary video: https://ziqiaopeng.github.io/emotalk

SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation

Recently, over-height vehicle strike frequently occurs, causing great economic cost and serious safety problems. Hence, an alert system which can accurately discover any possible height limiting devices in advance is necessary to be employed in modern large or medium sized cars, such as touring cars. Detecting and estimating the height limiting devices act as the key point of a successful height limit alert system. Though there are some works research height limit estimation, existing methods are either too computational expensive or not accurate enough. In this paper, we propose a novel stereo-based pipeline named SHLE for height limit estimation. Our SHLE pipeline consists of two stages. In stage 1, a novel devices detection and tracking scheme is introduced, which accurately locate the height limit devices in the left or right image. Then, in stage 2, the depth is temporally measured, extracted and filtered to calculate the height limit device. To benchmark the height limit estimation task, we build a large-scale dataset named "Disparity Height", where stereo images, pre-computed disparities and ground-truth height limit annotations are provided. We conducted extensive experiments on "Disparity Height" and the results show that SHLE achieves an average error below than 10cm though the car is 70m away from the devices. Our method also outperforms all compared baselines and achieves state-of-the-art performance. Code is available at https://github.com/Yang-Kaixing/SHLE.

FuRPE: Learning Full-body Reconstruction from Part Experts

Full-body reconstruction is a fundamental but challenging task. Owing to the lack of annotated data, the performances of existing methods are largely limited. In this paper, we propose a novel method named Full-body Reconstruction from Part Experts~(FuRPE) to tackle this issue. In FuRPE, the network is trained using pseudo labels and features generated from part-experts. An simple yet effective pseudo ground-truth selection scheme is proposed to extract high-quality pseudo labels. In this way, a large-scale of existing human body reconstruction datasets can be leveraged and contribute to the model training. In addition, an exponential moving average training strategy is introduced to train the network in a self-supervised manner, further boosting the performance of the model. Extensive experiments on several widely used datasets demonstrate the effectiveness of our method over the baseline. Our method achieves the state-of-the-art performance. Code will be publicly available for further research.