Yue Wang, Ruotian Ma, Xingyu Chen, Zhengliang Shi, Morunliu Yang, Wanshun Chen, Huang Liu, Jiadi Yao, Xin He, Qu Yang, Qingxuan Jiang, Fanghua Ye, Juntao Li, Zhaopeng Tu, Xiaolong Li, Liefeng Bo, Min Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, facial motion, head pose generation, and video quality. However, no model has yet led or tied on all these metrics due to the one-to-many mapping between audio and motion. In this paper, we propose VividTalk, a two-stage generic framework that supports generating high-visual quality talking head videos with all the above properties. Specifically, in the first stage, we map the audio to mesh by learning two motions, including non-rigid facial motion and rigid head motion. For facial motion, both blendshape and vertex are adopted as the intermediate representation to maximize the representation ability of the model. For head motion, a novel learnable head pose codebook with a two-phase training mechanism is proposed. In the second stage, we proposed a dual branch motion-vae and a generator to transform the meshes into dense motion and synthesize high-quality video frame-by-frame. Extensive experiments show that the proposed VividTalk can generate high-visual quality talking head videos with lip-sync and realistic enhanced by a large margin, and outperforms previous state-of-the-art works in objective and subjective comparisons. The code will be publicly released upon publication.

This paper introduces a new control signal for facial motion generation: timeline control. Compared to audio and text signals, timelines provide more fine-grained control, such as generating specific facial motions with precise timing. Users can specify a multi-track timeline of facial actions arranged in temporal intervals, allowing precise control over the timing of each action. To model the timeline control capability, We first annotate the time intervals of facial actions in natural facial motion sequences at a frame-level granularity. This process is facilitated by Toeplitz Inverse Covariance-based Clustering to minimize human labor. Based on the annotations, we propose a diffusion-based generation model capable of generating facial motions that are natural and accurately aligned with input timelines. Our method supports text-guided motion generation by using ChatGPT to convert text into timelines. Experimental results show that our method can annotate facial action intervals with satisfactory accuracy, and produces natural facial motions accurately aligned with timelines.

Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community, 3D works typically require multi-view captures for per-case training, which severely limits their applicability of modeling arbitrary characters in a short time. Recent 2D methods break this limitation via pre-trained diffusion models, but they struggle for flexible controls, pose generality and scene interaction. To this end, we propose MIMO, a novel framework which can not only synthesize realistic character videos with controllable attributes (i.e., character, motion and scene) provided by simple user inputs, but also simultaneously achieve advanced scalability to arbitrary characters, generality to novel 3D motions, and applicability to interactive real-world scenes in a unified framework. The core idea is to encode the 2D video to compact spatial codes, considering the inherent 3D nature of video occurrence. Concretely, we lift the 2D frame pixels into 3D using monocular depth estimators, and decompose the video clip into three spatial components (i.e., main human, underlying scene, and floating occlusion) in hierarchical layers based on the 3D depth. These components are further encoded to canonical identity code, structured motion code and full scene code, which are utilized as control signals of the synthesis process. The design of spatial decomposed modeling enables flexible user control, complex motion expression, as well as 3D-aware synthesis for scene interactions. Experimental results show that the proposed method outperforms prior works by a large margin in character animation synthesis and is effective in providing a high degree of controllability (i.e., arbitrary characters, novel 3D motions, interactive scenes), thus enabling brandnew editing tasks (e.g., video character replacement).

Generating animatable human avatars from a single image is essential for various digital human modeling applications. Existing 3D reconstruction methods often struggle to capture fine details in animatable models, while generative approaches for controllable animation, though avoiding explicit 3D modeling, suffer from viewpoint inconsistencies in extreme poses and computational inefficiencies. In this paper, we address these challenges by leveraging the power of generative models to produce detailed multi-view canonical pose images, which help resolve ambiguities in animatable human reconstruction. We then propose a robust method for 3D reconstruction of inconsistent images, enabling real-time rendering during inference. Specifically, we adapt a transformer-based video generation model to generate multi-view canonical pose images and normal maps, pretraining on a large-scale video dataset to improve generalization. To handle view inconsistencies, we recast the reconstruction problem as a 4D task and introduce an efficient 3D modeling approach using 4D Gaussian Splatting. Experiments demonstrate that our method achieves photorealistic, real-time animation of 3D human avatars from in-the-wild images, showcasing its effectiveness and generalization capability. Our code will be available on https://github.com/aigc3d/AniGS.

Text-guided 3D human generation has advanced with the development of efficient 3D representations and 2D-lifting methods like Score Distillation Sampling (SDS). However, current methods suffer from prolonged training times and often produce results that lack fine facial and garment details. In this paper, we propose GaussianIP, an effective two-stage framework for generating identity-preserving realistic 3D humans from text and image prompts. Our core insight is to leverage human-centric knowledge to facilitate the generation process. In stage 1, we propose a novel Adaptive Human Distillation Sampling (AHDS) method to rapidly generate a 3D human that maintains high identity consistency with the image prompt and achieves a realistic appearance. Compared to traditional SDS methods, AHDS better aligns with the human-centric generation process, enhancing visual quality with notably fewer training steps. To further improve the visual quality of the face and clothes regions, we design a View-Consistent Refinement (VCR) strategy in stage 2. Specifically, it produces detail-enhanced results of the multi-view images from stage 1 iteratively, ensuring the 3D texture consistency across views via mutual attention and distance-guided attention fusion. Then a polished version of the 3D human can be achieved by directly perform reconstruction with the refined images. Extensive experiments demonstrate that GaussianIP outperforms existing methods in both visual quality and training efficiency, particularly in generating identity-preserving results. Our code is available at: https://github.com/silence-tang/GaussianIP.

Video-to-audio generation is essential for synthesizing realistic audio tracks that synchronize effectively with silent videos. Following the perspective of extracting essential signals from videos that can precisely control the mature text-to-audio generative diffusion models, this paper presents how to balance the representation of mel-spectrograms in terms of completeness and complexity through a new approach called Mel Quantization-Continuum Decomposition (Mel-QCD). We decompose the mel-spectrogram into three distinct types of signals, employing quantization or continuity to them, we can effectively predict them from video by a devised video-to-all (V2X) predictor. Then, the predicted signals are recomposed and fed into a ControlNet, along with a textual inversion design, to control the audio generation process. Our proposed Mel-QCD method demonstrates state-of-the-art performance across eight metrics, evaluating dimensions such as quality, synchronization, and semantic consistency.

Motion-controllable image animation is a fundamental task with a wide range of potential applications. Recent works have made progress in controlling camera or object motion via various motion representations, while they still struggle to support collaborative camera and object motion control with adaptive control granularity. To this end, we introduce 3D-aware motion representation and propose an image animation framework, called Perception-as-Control, to achieve fine-grained collaborative motion control. Specifically, we construct 3D-aware motion representation from a reference image, manipulate it based on interpreted user instructions, and perceive it from different viewpoints. In this way, camera and object motions are transformed into intuitive and consistent visual changes. Then, our framework leverages the perception results as motion control signals, enabling it to support various motion-related video synthesis tasks in a unified and flexible way. Experiments demonstrate the superiority of the proposed approach. For more details and qualitative results, please refer to our anonymous project webpage: https://chen-yingjie.github.io/projects/Perception-as-Control.

This paper presents UniPortrait, an innovative human image personalization framework that unifies single- and multi-ID customization with high face fidelity, extensive facial editability, free-form input description, and diverse layout generation. UniPortrait consists of only two plug-and-play modules: an ID embedding module and an ID routing module. The ID embedding module extracts versatile editable facial features with a decoupling strategy for each ID and embeds them into the context space of diffusion models. The ID routing module then combines and distributes these embeddings adaptively to their respective regions within the synthesized image, achieving the customization of single and multiple IDs. With a carefully designed two-stage training scheme, UniPortrait achieves superior performance in both single- and multi-ID customization. Quantitative and qualitative experiments demonstrate the advantages of our method over existing approaches as well as its good scalability, e.g., the universal compatibility with existing generative control tools. The project page is at https://aigcdesigngroup.github.io/UniPortrait-Page/ .

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.

In this paper, we propose a novel diffusion-based multi-condition controllable framework for video head swapping, which seamlessly transplant a human head from a static image into a dynamic video, while preserving the original body and background of target video, and further allowing to tweak head expressions and movements during swapping as needed. Existing face-swapping methods mainly focus on localized facial replacement neglecting holistic head morphology, while head-swapping approaches struggling with hairstyle diversity and complex backgrounds, and none of these methods allow users to modify the transplanted head expressions after swapping. To tackle these challenges, our method incorporates several innovative strategies through a unified latent diffusion paradigm. 1) Identity-preserving context fusion: We propose a shape-agnostic mask strategy to explicitly disentangle foreground head identity features from background/body contexts, combining hair enhancement strategy to achieve robust holistic head identity preservation across diverse hair types and complex backgrounds. 2) Expression-aware landmark retargeting and editing: We propose a disentangled 3DMM-driven retargeting module that decouples identity, expression, and head poses, minimizing the impact of original expressions in input images and supporting expression editing. While a scale-aware retargeting strategy is further employed to minimize cross-identity expression distortion for higher transfer precision. Experimental results demonstrate that our method excels in seamless background integration while preserving the identity of the source portrait, as well as showcasing superior expression transfer capabilities applicable to both real and virtual characters.

The recent Segment Anything Models (SAMs) have emerged as foundational visual models for general interactive segmentation. Despite demonstrating robust generalization abilities, they still suffer performance degradations in scenarios demanding accurate masks. Existing methods for high-precision interactive segmentation face a trade-off between the ability to perceive intricate local details and maintaining stable prompting capability, which hinders the applicability and effectiveness of foundational segmentation models. To this end, we present an SAM2Refiner framework built upon the SAM2 backbone. This architecture allows SAM2 to generate fine-grained segmentation masks for both images and videos while preserving its inherent strengths. Specifically, we design a localization augment module, which incorporates local contextual cues to enhance global features via a cross-attention mechanism, thereby exploiting potential detailed patterns and maintaining semantic information. Moreover, to strengthen the prompting ability toward the enhanced object embedding, we introduce a prompt retargeting module to renew the embedding with spatially aligned prompt features. In addition, to obtain accurate high resolution segmentation masks, a mask refinement module is devised by employing a multi-scale cascaded structure to fuse mask features with hierarchical representations from the encoder. Extensive experiments demonstrate the effectiveness of our approach, revealing that the proposed method can produce highly precise masks for both images and videos, surpassing state-of-the-art methods.

Co-speech gesture generation must carefully integrate common rhythmic motion with rare yet essential semantic gestures. In this work, we propose SemTalk for holistic co-speech gesture generation with frame-level semantic emphasis. Our key insight is to separately learn base motions and sparse motions, and then adaptively fuse them. In particular, coarse2fine cross-attention module and rhythmic consistency learning are explored to establish rhythm-related base motion, ensuring a coherent foundation that synchronizes gestures with the speech rhythm. Subsequently, semantic emphasis learning is designed to generate semantic-aware sparse motion, focusing on frame-level semantic cues. Finally, to integrate sparse motion into the base motion and generate semantic-emphasized co-speech gestures, we further leverage a learned semantic score for adaptive synthesis. Qualitative and quantitative comparisons on two public datasets demonstrate that our method outperforms the state-of-the-art, delivering high-quality co-speech motion with enhanced semantic richness over a stable base motion.

Vision Transformers (ViT) are remarkable at 3D pose estimation, yet they still encounter certain challenges. One issue is that the popular ViT architecture for pose estimation is limited to images and lacks temporal information. Another challenge is that the prediction often fails to maintain pixel alignment with the original images. To address these issues, we propose a systematic framework for 3D pose estimation, called ExtPose. ExtPose extends image ViT to the challenging scenario and video setting by taking in additional 2D pose evidence and capturing temporal information in a full attention-based manner. We use 2D human skeleton images to integrate structured 2D pose information. By sharing parameters and attending across modalities and frames, we enhance the consistency between 3D poses and 2D videos without introducing additional parameters. We achieve state-of-the-art (SOTA) performance on multiple human and hand pose estimation benchmarks with substantial improvements to 34.0mm (-23%) on 3DPW and 4.9mm (-18%) on FreiHAND in PA-MPJPE over the other ViT-based methods respectively.

Fabricating and designing 3D garments has become extremely demanding with the increasing need for synthesizing realistic dressed persons for a variety of applications, e.g. 3D virtual try-on, digitalization of 2D clothes into 3D apparel, and cloth animation. It thus necessitates a simple and straightforward pipeline to obtain high-quality texture from simple input, such as 2D reference images. Since traditional warping-based texture generation methods require a significant number of control points to be manually selected for each type of garment, which can be a time-consuming and tedious process. We propose a novel method, called Cloth2Tex, which eliminates the human burden in this process. Cloth2Tex is a self-supervised method that generates texture maps with reasonable layout and structural consistency. Another key feature of Cloth2Tex is that it can be used to support high-fidelity texture inpainting. This is done by combining Cloth2Tex with a prevailing latent diffusion model. We evaluate our approach both qualitatively and quantitatively and demonstrate that Cloth2Tex can generate high-quality texture maps and achieve the best visual effects in comparison to other methods. For more details and animated results, please see https://tomguluson92. github.io/projects/cloth2tex/.

A radiance field is an effective representation of 3D scenes, which has been widely adopted in novel-view synthesis and 3D reconstruction. It is still an open and challenging problem to evaluate the geometry, i.e., the density field, as the ground-truth is almost impossible to obtain. One alternative indirect solution is to transform the density field into a point-cloud and compute its Chamfer Distance with the scanned ground-truth. However, many widely-used datasets have no point-cloud ground-truth since the scanning process along with the equipment is expensive and complicated. To this end, we propose a novel metric, named Inverse Mean Residual Color (IMRC), which can evaluate the geometry only with the observation images. Our key insight is that the better the geometry, the lower-frequency the computed color field. From this insight, given a reconstructed density field and observation images, we design a closed-form method to approximate the color field with low-frequency spherical harmonics, and compute the inverse mean residual color. Then the higher the IMRC, the better the geometry. Qualitative and quantitative experimental results verify the effectiveness of our proposed IMRC metric. We also benchmark several state-of-the-art methods using IMRC to promote future related research. Our code is available at https://github.com/qihangGH/IMRC.

Panoramic images enable deeper understanding and more holistic perception of 360° surrounding environment, which can naturally encode enriched scene context information compared to standard perspective image. Previous work has made lots of effort to solve the scene understanding task in a hybrid solution based on 2D-3D geometric reasoning, thus each sub-task is processed separately and few correlations are explored in this procedure. In this paper, we propose a fully 3D method for holistic indoor scene understanding which recovers the objects' shapes, oriented bounding boxes and the 3D room layout simultaneously from a single panorama. To maximize the exploration of the rich context information, we design a transformer-based context module to predict the representation and relationship among each component of the scene. In addition, we introduce a new dataset for scene understanding, including photo-realistic panoramas, high-fidelity depth images, accurately annotated room layouts, oriented object bounding boxes and shapes. Experiments on the synthetic and new datasets demonstrate that our method outperforms previous panoramic scene understanding methods in terms of both layout estimation and 3D object detection.

State-of-the-art man-made shape generative models usually adopt established generative models under a suitable implicit shape representation. A common theme is to perform distribution alignment, which does not explicitly model important shape priors. As a result, many synthetic shapes are not connected. Other synthetic shapes present problems of physical stability and geometric feasibility. This paper introduces a novel latent diffusion shape-generative model regularized by a quality checker that outputs a score of a latent code. The scoring function employs a learned function that provides a geometric feasibility score and a deterministic procedure to quantify a physical stability score. The key to our approach is a new diffusion procedure that combines the discrete empirical data distribution and a continuous distribution induced by the quality checker. We introduce a principled approach to determine the trade-off parameters for learning the denoising network at different noise levels. Experimental results show that our approach outperforms state-of-the-art shape generations quantitatively and qualitatively on ShapeNet-v2.

Lifting 2D diffusion for 3D generation is a challenging problem due to the lack of geometric prior and the complex entanglement of materials and lighting in natural images. Existing methods have shown promise by first creating the geometry through score-distillation sampling (SDS) applied to rendered surface normals, followed by appearance modeling. However, relying on a 2D RGB diffusion model to optimize surface normals is suboptimal due to the distribution discrepancy between natural images and normals maps, leading to instability in optimization. In this paper, recognizing that the normal and depth information effectively describe scene geometry and be auto-matically estimated from images, we propose to learn a generalizable Normal-Depth diffusion model for 3D generation. We achieve this by training on the large-scale LAION dataset together with the generalizable image-to-depth and normal prior models. In an attempt to alleviate the mixed illumination effects in the generated materials, we introduce an albedo diffusion model to impose data-driven constraints on the albedo component. Our experiments show that when integrated into existing text-to-3D pipelines, our models significantly enhance the detail richness, achieving state-of-the-art results. Our project page is at https://aigc3d.github.io/richdreamer/.

Generalizable 3D object reconstructionfrom single-view RGB-D images remains a challenging task, particularly with real-world data. Current state-of-the-art methods develop Transformer-based implicit field learning, necessitating an intensive learning paradigm that requires dense query-supervision uniformly sampled throughout the entire space. We propose a novel approach, IPoD, which harmonizes implicit field learning with point diffusion. This approach treats the query points for implicit field learning as a noisy point cloud for iterative denoising, allowing for their dynamic adaptation to the target object shape. Such adaptive query points harness diffusion learning's capability for coarse shape recovery and also enhances the implicit representation's ability to delineate finer details. Besides, an additional self-conditioning mechanism is designed to use implicit predictions as the guidance of diffusion learning, leading to a cooperative system. Experiments conducted on the CO3D-v2 dataset affirm the superiority of IPoD, achieving 7.8% improvement in F-score and 28.6% in Chamfer distance over existing methods. The generalizability of IPoD is also demonstrated on the MVImgNet dataset. Our project page is at https://yushuang-wu.github.io/IPoD.

Motion generation from discrete quantization offers many advantages over continuous regression, but at the cost of inevitable approximation errors. Previous methods usually quantize the entire body pose into one code, which not only faces the difficulty in encoding all joints within one vector but also loses the spatial relationship between different joints. Differently, in this work we quantize each individual joint into one vector, which i) simplifies the quantization process as the complexity associated with a single joint is markedly lower than that of the entire pose; ii) maintains a spatial-temporal structure that preserves both the spatial relationships among joints and the temporal movement patterns; iii) yields a 2D token map, which enables the application of various 2D operations widely used in 2D images. Grounded in the 2D motion quantization, we build a spatial-temporal modeling framework, where 2D joint VQVAE, temporal-spatial 2D masking technique, and spatial-temporal 2D attention are proposed to take advantage of spatial-temporal signals among the 2D tokens. Extensive experiments demonstrate that our method significantly outperforms previous methods across different datasets, with a $26.6\%$ decrease of FID on HumanML3D and a $29.9\%$ decrease on KIT-ML.

This paper studies the problem of estimating physical properties (system identification) through visual observations. To facilitate geometry-aware guidance in physical property estimation, we introduce a novel hybrid framework that leverages 3D Gaussian representation to not only capture explicit shapes but also enable the simulated continuum to render object masks as 2D shape surrogates during training. We propose a new dynamic 3D Gaussian framework based on motion factorization to recover the object as 3D Gaussian point sets across different time states. Furthermore, we develop a coarse-to-fine filling strategy to generate the density fields of the object from the Gaussian reconstruction, allowing for the extraction of object continuums along with their surfaces and the integration of Gaussian attributes into these continuum. In addition to the extracted object surfaces, the Gaussian-informed continuum also enables the rendering of object masks during simulations, serving as 2D-shape guidance for physical property estimation. Extensive experimental evaluations demonstrate that our pipeline achieves state-of-the-art performance across multiple benchmarks and metrics. Additionally, we illustrate the effectiveness of the proposed method through real-world demonstrations, showcasing its practical utility. Our project page is at https://jukgei.github.io/project/gic.

Recommender systems have been demonstrated to be effective to meet user's personalized interests for many online services (e.g., E-commerce and online advertising platforms). Recent years have witnessed the emerging success of many deep-learning-based recommendation models for augmenting collaborative filtering (CF) architectures with various neural network architectures, such as multilayer perceptron and autoencoder. However, the majority of them model the user-item relationship with single type of interaction, while overlooking the diversity of user behaviors on interacting with items, which can be click, add-to-cart, tag-as-favorite, and purchase. Such various types of interaction behaviors have great potential in providing rich information for understanding the user preferences. In this article, we pay special attention on user-item relationships with the exploration of multityped user behaviors. Technically, we contribute a new multi-behavior graph neural network (MBRec), which specially accounts for diverse interaction patterns and the underlying cross-type behavior interdependencies. In the MBRec framework, we develop a graph-structured learning framework to perform expressive modeling of high-order connectivity in behavior-aware user-item interaction graph. After that, a mutual relationship encoder is proposed to adaptively uncover complex relational structures and make aggregations across layer-specific behavior representations. Through comprehensive evaluation on real-world datasets, the advantages of our MBRec method have been validated under different experimental settings. Further analysis verifies the positive effects of incorporating the multi-behavioral context into the recommendation paradigm. In addition, the conducted case studies offer insights into the interpretability of user multi-behavior representations. We release our model implementation at https://github.com/akaxlh/MBRec.

This work addresses the challenge of high-quality surface normal estimation from monocular colored inputs (i.e., images and videos), a field which has recently been revolutionized by repurposing diffusion priors. However, previous attempts still struggle with stochastic inference, conflicting with the deterministic nature of the Image2Normal task, and costly ensembling step, which slows down the estimation process. Our method, StableNormal, mitigates the stochasticity of the diffusion process by reducing inference variance, thus producing "Stable-and-Sharp" normal estimates without any additional ensembling process. StableNormal works robustly under challenging imaging conditions, such as extreme lighting, blurring, and low quality. It is also robust against transparent and reflective surfaces, as well as cluttered scenes with numerous objects. Specifically, StableNormal employs a coarse-to-fine strategy, which starts with a one-step normal estimator (YOSO) to derive an initial normal guess, that is relatively coarse but reliable, then followed by a semantic-guided refinement process (SG-DRN) that refines the normals to recover geometric details. The effectiveness of StableNormal is demonstrated through competitive performance in standard datasets such as DIODE-indoor, iBims, ScannetV2 and NYUv2, and also in various downstream tasks, such as surface reconstruction and normal enhancement. These results evidence that StableNormal retains both the "stability" and "sharpness" for accurate normal estimation. StableNormal represents a baby attempt to repurpose diffusion priors for deterministic estimation. To democratize this, code and models have been publicly available in hf.co/Stable-X.

Approximating radiance fields with discretized volumetric grids is one of promising directions for improving NeRFs, represented by methods like DVGO, Plenoxels and TensoRF, which achieve super-fast training convergence and real-time rendering. However, these methods typically require a tremendous storage overhead, costing up to hundreds of megabytes of disk space and runtime memory for a single scene. We address this issue in this paper by introducing a simple yet effective framework, called vector quantized radiance fields (VQRF), for compressing these volume-grid-based radiance fields. We first present a robust and adaptive metric for estimating redundancy in grid models and performing voxel pruning by better exploring intermediate outputs of volumetric rendering. A trainable vector quantization is further proposed to improve the compactness of grid models. In combination with an efficient joint tuning strategy and post-processing, our method can achieve a compression ratio of 100× by reducing the overall model size to 1 MB with negligible loss on visual quality. Extensive experiments demonstrate that the proposed framework is capable of achieving unrivaled performance and well generalization across multiple methods with distinct volumetric structures, facilitating the wide use of volumetric radiance fields methods in real-world applications. Code is available at https://github.com/AlgoHunt/VQRF.

Talking head generation aims to generate faces that maintain the identity information of the source image and imitate the motion of the driving image. Most pioneering methods rely primarily on 2D representations and thus will inevitably suffer from face distortion when large head rotations are encountered. Recent works instead employ explicit 3D structural representations or implicit neural rendering to improve performance under large pose changes. Nevertheless, the fidelity of identity and expression is not so desirable, especially for novel-view synthesis. In this paper, we propose HiDe-NeRF, which achieves high-fidelity and free-view talking-head synthesis. Drawing on the recently proposed Deformable Neural Radiance Fields, HiDe-NeRF represents the 3D dynamic scene into a canonical appearance field and an implicit deformation field, where the former comprises the canonical source face and the latter models the driving pose and expression. In particular, we improve fidelity from two aspects: (i) to enhance identity expressiveness, we design a generalized appearance module that leverages multi-scale volume features to preserve face shape and details; (ii) to improve expression preciseness, we propose a lightweight deformation module that explicitly decouples the pose and expression to enable precise expression modeling. Extensive experiments demonstrate that our proposed approach can generate better results than previous works. Project page: https://www.waytron.net/hidenerf/

Towards stable human pose estimation from monocular images, there remain two main dilemmas. On the one hand, the different perspectives, i.e., front view, side view, and top view, appear the inconsistent performances due to the depth ambiguity. On the other hand, foot posture plays a significant role in complicated human pose estimation, i.e., dance and sports, and foot-ground interaction, but unfortunately, it is omitted in most general approaches and datasets. In this paper, we first propose the Cross-View Fusion (CVF) module to catch up with better 3D intermediate representation and alleviate the view inconsistency based on the vision transformer encoder. Then the optimization-based method is introduced to reconstruct the foot pose and foot-ground contact for the general multi-view datasets including AIST++ and Human3.6M. Besides, the reversible kinematic topology strategy is innovated to utilize the contact information into the full-body with foot pose regressor. Extensive experiments on the popular benchmarks demonstrate that our method outperforms the state-of-the-art approaches by achieving 40.1mm PA-MPJPE on the 3DPW test set and 43.8mm on the AIST++ test set.

The current interacting hand (IH) datasets are relatively simplistic in terms of background and texture, with hand joints being annotated by a machine annotator, which may result in inaccuracies, and the diversity of pose distribution is limited. However, the variability of background, pose distribution, and texture can greatly influence the generalization ability. Therefore, we present a large-scale synthetic dataset –RenderIH– for interacting hands with accurate and diverse pose annotations. The dataset contains 1M photo-realistic images with varied backgrounds, perspectives, and hand textures. To generate natural and diverse interacting poses, we propose a new pose optimization algorithm. Additionally, for better pose estimation accuracy, we introduce a transformer-based pose estimation network, TransHand, to leverage the correlation between interacting hands and verify the effectiveness of RenderIH in improving results. Our dataset is model-agnostic and can improve more accuracy of any hand pose estimation method in comparison to other real or synthetic datasets. Experiments have shown that pretraining on our synthetic data can significantly decrease the error from 6.76mm to 5.79mm, and our Transhand surpasses contemporary methods. Our dataset and code are available at https://github.com/adwardlee/RenderIH.

Many virtual reality applications require massive 3D content, which impels the need for low-cost and efficient modeling tools in terms of quality and quantity. In this paper, we present a Diffusion-augmented Generative model to generate high-fidelity 3D textured meshes that can be directly used in modern graphics engines. Challenges in directly generating textured mesh arise from the instability and texture incompleteness of a hybrid framework which contains conversion between 2D features and 3D space. To alleviate these difficulties, DG3D incorporates a diffusion-based augmentation module into the min-max game between the 3D tetrahedral mesh generator and 2D renderings discriminators, which stabilizes network optimization and prevents mode collapse in vanilla GANs. We also suggest using multi-modal renderings in discrimination to further increase the aesthetics and completeness of generated textures. Extensive experiments on the public benchmark and real scans show that our proposed DG3D outperforms existing state-of-the-art methods by a large margin, i.e., 5% ∼ 40% in FID-3D score and 5%∼10% in geometry-related metrics. Code is available at https://github.com/seakforzq/DG3D.

A neural radiance field (NeRF) enables the synthesis of cutting-edge realistic novel view images of a 3D scene. It includes density and color fields to model the shape and radiance of a scene, respectively. Supervised by the photometric loss in an end-to-end training manner, NeRF inherently suffers from the shape-radiance ambiguity problem, i.e., it can perfectly fit training views but does not guarantee decoupling the two fields correctly. To deal with this issue, existing works have incorporated prior knowledge to provide an independent supervision signal for the density field, including total variation loss, sparsity loss, distortion loss, etc. These losses are based on general assumptions about the density field, e.g., it should be smooth, sparse, or compact, which are not adaptive to a specific scene. In this paper, we propose a more adaptive method to reduce the shape-radiance ambiguity. The key is a rendering method that is only based on the density field. Specifically, we first estimate the color field based on the density field and posed images in a closed form. Then NeRF's rendering process can proceed. We address the problems in estimating the color field, including occlusion and non-uniformly distributed views. Afterwards, it is applied to regularize NeRF's density field. As our regularization is guided by photometric loss, it is more adaptive compared to existing ones. Experimental results show that our method improves the density field of NeRF both qualitatively and quantitatively. Our code is available at https://github.com/qihangGH/Closed-form-color-field.

In this paper, we propose a simple yet effective video super-resolution method that aims at generating highfidelity high-resolution (HR) videos from low-resolution (LR) ones. Previous methods predominantly leverage temporal neighbor frames to assist the super-resolution of the current frame. Those methods achieve limited performance as they suffer from the challenges in spatial frame alignment and the lack of useful information from similar LR neighbor frames. In contrast, we devise a cross-frame non-local attention mechanism that allows video superresolution without frame alignment, leading to being more robust to large motions in the video. In addition, to acquire general video prior information beyond neighbor frames, and to compensate for the information loss caused by large motions, we design a novel memory-augmented attention module to memorize general video details during the superresolution training. We have thoroughly evaluated our work on various challenging datasets. Compared to other recent video super-resolution approaches, our method not only achieves significant performance gains on large motion videos but also shows better generalization. Our source code and the new Parkour benchmark dataset is available at https://github.com/jiy173/MANA.

Session-based recommendation plays a central role in a wide spectrum of online applications, ranging from e-commerce to online advertising services. However, the majority of existing session-based recommendation techniques (e.g., attention-based recurrent network or graph neural network) are not well-designed for capturing the complex transition dynamics exhibited with temporally-ordered and multi-level interdependent relation structures. These methods largely overlook the relation hierarchy of item transitional patterns. In this paper, we propose a multi-task learning framework with Multi-level Transition Dynamics (MTD), which enables the jointly learning of intra- and inter-session item transition dynamics in automatic and hierarchical manner. Towards this end, we first develop a position-aware attention mechanism to learn item transitional regularities within individual session. Then, a graph-structured hierarchical relation encoder is proposed to explicitly capture the cross-session item transitions in the form of high-order connectivities by performing embedding propagation with the global graph context. The learning process of intra- and inter-session transition dynamics are integrated, to preserve the underlying low- and high-level item relationships in a common latent space. Extensive experiments on three real-world datasets demonstrate the superiority of MTD as compared to state-of-the-art baselines.

Social recommendation task aims to predict users' preferences over items with the incorporation of social connections among users, so as to alleviate the sparse issue of collaborative filtering. While many recent efforts show the effectiveness of neural network-based social recommender systems, several important challenges have not been well addressed yet: (i) The majority of models only consider users’ social connections, while ignoring the inter-dependent knowledge across items; (ii) Most of existing solutions are designed for singular type of user-item interactions, making them infeasible to capture the interaction heterogeneity; (iii) The dynamic nature of user-item interactions has been less explored in many social-aware recommendation techniques. To tackle the above challenges, this work proposes a Knowledge-aware Coupled Graph Neural Network (KCGN) that jointly injects the inter-dependent knowledge across items and users into the recommendation framework. KCGN enables the high-order user- and item-wise relation encoding by exploiting the mutual information for global graph structure awareness. Additionally, we further augment KCGN with the capability of capturing dynamic multi-typed user-item interactive patterns. Experimental studies on real-world datasets show the effectiveness of our method against many strong baselines in a variety of settings. Source codes are available at: https://github.com/xhcdream/KCGN.

Accurate user and item embedding learning is crucial for modern recommender systems. However, most existing recommendation techniques have thus far focused on modeling users' preferences over singular type of user-item interactions. Many practical recommendation scenarios involve multi-typed user interactive behaviors (e.g., page view, add-to-favorite and purchase), which presents unique challenges that cannot be handled by current recommendation solutions. In particular: i) complex inter-dependencies across different types of user behaviors; ii) the incorporation of knowledge-aware item relations into the multi-behavior recommendation framework; iii) dynamic characteristics of multi-typed user-item interactions. To tackle these challenges, this work proposes a Knowledge-Enhanced Hierarchical Graph Transformer Network (KHGT), to investigate multi-typed interactive patterns between users and items in recommender systems. Specifically, KHGT is build upon a graph-structured neural architecture to i) capture type-specific behavior semantics; ii) explicitly discriminate which types of user-item interactions are more important in assisting the forecasting task on the target behavior. Additionally, we further integrate the multi-modal graph attention layer with temporal encoding strategy, to empower the learned embeddings be reflective of both dedicated multiplex user-item and item-item collaborative relations, as well as the underlying interaction dynamics. Extensive experiments conducted on three real-world datasets show that KHGT consistently outperforms many state-of-the-art recommendation methods across various evaluation settings. Our implementation is available in https://github.com/akaxlh/KHGT.

Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment. While previous work has made significant efforts to learn traffic temporal dynamics and spatial dependencies, two key limitations exist in current models. First, only the neighboring spatial correlations among adjacent regions are considered in most existing methods, and the global interregion dependency is ignored. Additionally, these methods fail to encode the complex traffic transition regularities exhibited with time-dependent and multi-resolution in nature. To tackle these challenges, we develop a new traffic prediction framework–Spatial-Temporal Graph Diffusion Network (ST-GDN). In particular, ST-GDN is a hierarchically structured graph neural architecture which learns not only the local region-wise geographical dependencies, but also the spatial semantics from a global perspective. Furthermore, a multi-scale attention network is developed to empower ST-GDN with the capability of capturing multi-level temporal dynamics. Experiments on four real-life traffic datasets demonstrate that ST-GDN outperforms different types of state-of-the-art baselines.

In recent years, researchers attempt to utilize online social information to alleviate data sparsity for collaborative filtering, based on the rationale that social networks offers the insights to understand the behavioral patterns. However, due to the overlook of inter-dependent knowledge across items (e.g., knowledge graph dependencies between products), existing social recommender systems are insufficient to distill the heterogeneous collaborative signals from both user and item side. In this work, we propose Self- Supervised Metagraph Informax Network (SMIN) which investigates the potential of jointly incorporating social- and knowledge-aware relational structures into the user preference representation framework. To model relation heterogeneity, we design a metapath-guided heterogeneous graph neural network to aggregate feature embeddings from different types of meta-relations across users and items, empowering SMIN to maintain dedicated representations for multifaceted user- and item-wise dependencies. Additionally, to inject high-order collaborative signals into recommendation, we generalize the mutual information learning paradigm from vector space to a self-supervised graph-based collaborative filtering. This endows the expressive modeling of user-item interactive patterns, by exploring global-level collaborative relations and underlying isomorphic transformation property of graph topology. Experimental results on several real-world datasets demonstrate the effectiveness of our model over various state-of-the-art recommendation methods. Further analysis provides insights into the performance superiority of our new recommendation framework. We release our source code at https://github.com/SocialRecsys/SMIN.

To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured large-scale dataset, named as DroneCrowd, formed by 112 video clips with 33, 600 HD frames in various scenarios. Notably, we annotate 20, 800 people trajectories with 4.8 million heads and several video-level attributes. Meanwhile, we design the Space-Time Neighbor-Aware Network (STNNet) as a strong baseline to solve object detection, tracking and counting jointly in dense crowds. STNNet is formed by the feature extraction module, followed by the density map estimation heads, and localization and association subnets. To exploit the context information of neighboring objects, we design the neighboring context loss to guide the association subnet training, which enforces consistent relative position of nearby objects in temporal domain. Extensive experiments on our DroneCrowd dataset demonstrate that STNNet performs favorably against the state-of-the-arts.

Fraud detection is extremely critical for e-commerce business platforms. Utilizing graph structure data and identifying unexpected dense subgraphs as suspicious is a category of commonly used fraud detection methods. Among them, spectral methods solve the problem efficiently but hurt the performance due to the relaxed constraints. Heuristic methods cannot be accelerated with parallel computation and fail to control the scope of returned suspicious nodes. These drawbacks affect the real-world applications of existing graph-based methods. In this paper, we propose an Ensemble based Fraud DETection (ENSEMFDET) method to scale up fraud detection in bipartite graphs. By oversampling the graph and solving the subproblems, the ensemble approach further votes suspicious nodes without sacrificing the prediction accuracy. Extensive experiments have been done on real transaction data from JD.com and demonstrate the effectiveness, practicability, and scalability of ENSEMFDET.

Many previous studies aim to augment collaborative filtering with deep neural network techniques, so as to achieve better recommendation performance. However, most existing deep learning-based recommender systems are designed for modeling singular type of user-item interaction behavior, which can hardly distill the heterogeneous relations between user and item. In practical recommendation scenarios, there exist multi-typed user behaviors, such as browse and purchase. Due to the overlook of user's multi-behavioral patterns over different items, existing recommendation methods are insufficient to capture heterogeneous collaborative signals from user multi-behavior data. Inspired by the strength of graph neural networks for structured data modeling, this work proposes a Graph Neural Multi-Behavior Enhanced Recommendation (GNMR) framework which explicitly models the dependencies between different types of user-item interactions under a graph-based message passing architecture. GNMR devises a relation aggregation network to model interaction heterogeneity, and recursively performs embedding propagation between neighboring nodes over the user-item interaction graph. Experiments on real-world recommendation datasets show that our GNMR consistently outperforms state-of-the-art methods. The source code is available at https://github.com/akaxlh/GNMR.

Crime prediction is crucial for public safety and resource optimization, yet is very challenging due to two aspects: i) the dynamics of criminal patterns across time and space, crime events are distributed unevenly on both spatial and temporal domains; ii) time-evolving dependencies between different types of crimes (e.g., Theft, Robbery, Assault, Damage) which reveal fine-grained semantics of crimes. To tackle these challenges, we propose Spatial-Temporal Sequential Hypergraph Network (ST-SHN) to collectively encode complex crime spatial-temporal patterns as well as the underlying category-wise crime semantic relationships. In specific, to handle spatial-temporal dynamics under the long-range and global context, we design a graph-structured message passing architecture with the integration of the hypergraph learning paradigm. To capture category-wise crime heterogeneous relations in a dynamic environment, we introduce a multi-channel routing mechanism to learn the time-evolving structural dependency across crime types. We conduct extensive experiments on two real-word datasets, showing that our proposed ST-SHN framework can significantly improve the prediction performance as compared to various state-of-the-art baselines. The source code is available at https://github.com/akaxlh/ST-SHN.

Vertical federated learning (VFL) is an effective paradigm of training the emerging cross-organizational (e.g., different corporations, companies and organizations) collaborative learning with privacy preserving. Stochastic gradient descent (SGD) methods are the popular choices for training VFL models because of the low per-iteration computation. However, existing SGD-based VFL algorithms are communication-expensive due to a large number of communication rounds. Meanwhile, most existing VFL algorithms use synchronous computation which seriously hamper the computation resource utilization in real-world applications. To address the challenges of communication and computation resource utilization, we propose an asynchronous stochastic quasi-Newton (AsySQN) framework for VFL, under which three algorithms, i.e. AsySQN-SGD, -SVRG and -SAGA, are proposed. The proposed AsySQN-type algorithms making descent steps scaled by approximate (without calculating the inverse Hessian matrix explicitly) Hessian information convergence much faster than SGD-based methods in practice and thus can dramatically reduce the number of communication rounds. Moreover, the adopted asynchronous computation can make better use of the computation resource. We theoretically prove the convergence rates of our proposed algorithms for strongly convex problems. Extensive numerical experiments on real-word datasets demonstrate the lower communication costs and better computation resource utilization of our algorithms compared with state-of-the-art VFL algorithms.

Modern recommender systems often embed users and items into low-dimensional latent representations, based on their observed interactions. In practical recommendation scenarios, users often exhibit various intents which drive them to interact with items with multiple behavior types (e.g., click, tag-as-favorite, purchase). However, the diversity of user behaviors is ignored in most of existing approaches, which makes them difficult to capture heterogeneous relational structures across different types of interactive behaviors. Exploring multi-typed behavior patterns is of great importance to recommendation systems, yet is very challenging because of two aspects: i) The complex dependencies across different types of user-item interactions; ii) Diversity of such multi-behavior patterns may vary by users due to their personalized preference. To tackle the above challenges, we propose a Multi-Behavior recommendation framework with Graph Meta Network to incorporate the multi-behavior pattern modeling into a meta-learning paradigm. Our developed MB-GMN empowers the user-item interaction learning with the capability of uncovering type-dependent behavior representations, which automatically distills the behavior heterogeneity and interaction diversity for recommendations. Extensive experiments on three real-world datasets show the effectiveness of MB-GMN by significantly boosting the recommendation performance as compared to various state-of-the-art baselines. The source code is available at https://github.com/akaxlh/MB-GMN.

Style transfer on images has achieved significant advances in recent years, with the deep convolutional neural network (CNN). Directly applying image style transfer algorithms to each frame of a video independently often leads to flickering and unstable results. In this work, we present a self-supervised space-time convolutional neural network (CNN) based method for online video style transfer, named as VTNet, which is end-to-end trained from nearly unlimited unlabeled video data to produce temporally coherent stylized videos in real-time. Specifically, our VTNet transfer the style of a reference image to the source video frames, which is formed by the temporal prediction branch and the stylizing branch. The temporal prediction branch is used to capture discriminative spatiotemporal features for temporal consistency, pretrained in an adversarial manner from unlabeled video data. The stylizing branch is used to transfer the style image to a video frame with the guidance from the temporal prediction branch to ensure temporal consistency. To guide the training of VTNet, we introduce the style-coherence loss net (SCNet), which assembles the content loss, the style loss, and the new designed coherence loss. These losses are computed based on high-level features extracted from a pretrained VGG-16 network. The content loss is used to preserve high-level abstract contents of the input frames, and the style loss introduces new colors and patterns from the style image. Instead of using optical flow to explicitly redress the stylized video frames, we design the coherence loss to make the stylized video inherit the dynamics and motion patterns from the source video to remove temporal flickering. Extensive subjective and objective evaluations on various styles demonstrate that the proposed method achieves favorable results against the state-of-the-arts with high efficiency.

Anomaly detection is a useful technique in many applications such as network security and fraud detection. Due to the insufficiency of anomaly samples as training data, it is usually formulated as an unsupervised model learning problem. In recent years there is a surge of adopting graph data structure in numerous applications. Detecting anomaly in an attributed network is more challenging than the sample based task because of the sample information representations in the form of graph nodes and edges. In this paper, we propose a generative adversarial attributed network (GAAN) anomaly detection framework. The fake graph nodes are generated by a generator module with Gaussian noise as input. An encoder module is employed to map both real and fake graph nodes into a latent space. To encode the graph structure information into the node latent representation, we compute the sample covariance matrix for real nodes and fake nodes respectively. A discriminator is trained to recognize whether two connected nodes are from the real or fake graph. With the learned encoder module output, an anomaly evaluation measurement considering the sample reconstruction error and real-sample identification confidence is employed to make prediction. We conduct extensive experiments on benchmark datasets and compare with state-of-the-art attributed graph anomaly detection methods. The superior AUC score demonstrates the effectiveness of the proposed method.

Session-based recommendation is critical in modern recommender systems, which aims to predict the next interested item given anonymous behavior sequences of users. While prior works have made efforts to addressing the session-based recommendation problem, two significant limitations exist: i) They ignore the fact that items may be correlated with other across different session units; ii) existing solutions are also limited in their assumption of rigidly ordered pattern over intra-session item transition, which may not be true in practice. To address these above limitations, we propose a Local-Global Session-based Recommendation framework–LGSR which generalizes the modeling of behavior dynamics from two perspectives: we first design a cross-session item dependency encoder to learn the inter-session item relation structures from a global perspective. Additionally, a dual-stage attentive aggregation module is developed to capture local item transition dynamics, without the restriction of rigid sequential process for jointly modeling user's current interest and intra-session purpose. With the exploration of both complex intra- and inter-session interest transitional regularities, our LGSR model enables the representation learning of user behavior dynamics via jointly mapping local and global signals into the same latent space. The experimental results on two real-world datasets demonstrate the superiority of the proposed LGSR framework over state-of-the-art methods.

Pig counting is a crucial task for large-scale pig farming. Pigs are usually visually counted by human. But this process is very time-consuming and error-prone. Few studies in literature developed automated pig counting method. The existing works only focused on pig counting using single image, and its level of accuracy faced challenges due to pig movements, occlusion and overlapping. Especially, the field of view of a single image is very limited, and could not meet the needs of pig counting for large pig grouping houses. Towards addressing these challenges, we presented a real-time automated pig counting system in crowds using only one monocular fisheye camera with an inspection robot. Our system showed that it achieved performance superior to human. Our pipeline began with a novel bottom-up pig detection algorithm to avoid false negatives due to overlapping, occlusion and deformable pig shapes. This detection included a deep convolution neural network (CNN) for pig body part keypoints detection and the keypoints association method to identify individual pigs. It then employed an efficient on-line tracking method to associate pigs across image frames. Finally, pig counts were estimated by a novel spatial-aware temporal response filtering (STRF) method to suppress false positives caused by pig or camera movements or tracking failures. The whole pipeline has been deployed in an edge computing device, and demonstrated the effectiveness.

Predicting anomalies (e.g., blocked driveway and vehicle collisions) in urban space plays an important role in assisting governments and communities for building smart city applications, ranging from intelligent transportation to public safety. However, predicting urban anomalies is not trivial due to the following two factors: i) The sequential transition regularities of anomaly occurrences is complex, which exhibit with high-order and dynamic correlations. ii) The Interactions between region, time and anomaly category is multi-dimensional in real-world urban anomaly forecasting scenario. How to fuse multiple relations from spatial, temporal and categorical dimensions in the predictive framework remains a significant challenge. To address these two challenges, we propose a Cross-Interaction Hierarchical Attention network model (CHAT) which uncovers the dynamic occurrence patterns of time-stamped urban anomaly data. Our CHAT framework could automatically capture the relevance of past anomaly occurrences across different time steps, and discriminates which types of cross-modal interactions are more important for making future predictions. Experiment results demonstrate the superiority of CHAT framework over state-of-the-art baselines.

Capturing users' precise preferences is of great importance in various recommender systems (e.g., e-commerce platforms and online advertising sites), which is the basis of how to present personalized interesting product lists to individual users. In spite of significant progress has been made to consider relations between users and items, most of existing recommendation techniques solely focus on singular type of user-item interactions. However, user-item interactive behavior is often exhibited with multi-type (e.g., page view, add-to-favorite and purchase) and inter-dependent in nature. The overlook of multiplex behavior relations can hardly recognize the multi-modal contextual signals across different types of interactions, which limit the feasibility of current recommendation methods. To tackle the above challenge, this work proposes a Memory-Augmented Transformer Networks (MATN), to enable the recommendation with multiplex behavioral relational information, and joint modeling of type-specific behavioral context and type-wise behavior inter-dependencies, in a fully automatic manner. In our MATN framework, we first develop a transformer-based multi-behavior relation encoder, to make the learned interaction representations be reflective of the cross-type behavior relations. Furthermore, a memory attention network is proposed to supercharge MATN capturing the contextual signals of different types of behavior into the category-specific latent embedding space. Finally, a cross-behavior aggregation component is introduced to promote the comprehensive collaboration across type-aware interaction behavior representations, and discriminate their inherent contributions in assisting recommendations. Extensive experiments on two benchmark datasets and a real-world e-commence user behavior data demonstrate significant improvements obtained by MATN over baselines. Codes are available at: https://github.com/akaxlh/MATN.

Traffic accident forecasting is a vital part of intelligent transportation systems in urban sensing. However, predicting traffic accidents is not trivial because of two key challenges: i) the complexities of external factors which are presented with heterogeneous data structures; ii) the complex sequential transition regularities exhibited with time-dependent and high-order inter-correlations. To address these challenges, we develop a deep Dynamic Fusion Network framework (DFN), to explore the central theme of improving the ability of deep neural network on modeling heterogeneous external factors in a fully dynamic manner for traffic accident forecasting. Specifically, DFN first develops an integrative architecture, i.e., with the cooperation of a context-aware embedding module and a hierarchical fusion network, to effectively transferring knowledge from different external units for spatial-temporal pattern learning across space and time. After that, we further develop a temporal aggregation neural network layer to automatically capture relevance scores from the temporal dimension. Through extensive experiments on real-world data collected from New York City, we validate the effectiveness of our framework against various competitive methods. Besides, we also provide a qualitative analysis on prediction results to show the model interpretability.

In this paper, we present a unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segmentation branch. Specifically, the temporal coherence branch pretrained in an adversarial fashion from unlabeled video data, is designed to capture the dynamic appearance and motion cues of video sequences to guide object segmentation. The spatial segmentation branch focuses on segmenting objects accurately based on the learned appearance and motion cues. To obtain accurate segmentation results, we design a coarse-to-fine process to sequentially apply a designed attention module on multi-scale feature maps, and concatenate them to produce the final prediction. In this way, the spatial segmentation branch is enforced to gradually concentrate on object regions. These two branches are jointly fine-tuned on video segmentation sequences in an end-to-end manner. Several experiments are carried out on three challenging datasets (i.e., DAVIS-2016, DAVIS-2017 and Youtube-Object) to show that our method achieves favorable performance against the state-of-the-arts. Code is available at https://github.com/longyin880815/STCNN.

Current state-of-the-art object objectors are fine-tuned from the off-the-shelf networks pretrained on large-scale classification dataset ImageNet, which incurs some additional problems: 1) The classification and detection have different degrees of sensitivity to translation, resulting in the learning objective bias; 2) The architecture is limited by the classification network, leading to the inconvenience of modification. To cope with these problems, training detectors from scratch is a feasible solution. However, the detectors trained from scratch generally perform worse than the pretrained ones, even suffer from the convergence issue in training. In this paper, we explore to train object detectors from scratch robustly. By analysing the previous work on optimization landscape, we find that one of the overlooked points in current trained-from-scratch detector is the BatchNorm. Resorting to the stable and predictable gradient brought by BatchNorm, detectors can be trained from scratch stably while keeping the favourable performance independent to the network architecture. Taking this advantage, we are able to explore various types of networks for object detection, without suffering from the poor convergence. By extensive experiments and analyses on downsampling factor, we propose the Root-ResNet backbone network, which makes full use of the information from original images. Our ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods. Codes will be made publicly available at https://github.com/KimSoybean/ScratchDet.

Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. However, the loss function for heatmap regression is rarely studied. In this paper, we analyze the ideal loss function properties for heatmap regression in face alignment problems. Then we propose a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels. This adaptability penalizes loss more on foreground pixels while less on background pixels. To address the imbalance between foreground and background pixels, we also propose Weighted Loss Map, which assigns high weights on foreground and difficult background pixels to help training process focus more on pixels that are crucial to landmark localization. To further improve face alignment accuracy, we introduce boundary prediction and CoordConv with boundary coordinates. Extensive experiments on different benchmarks, including COFW, 300W and WFLW, show our approach outperforms the state-of-the-art by a significant margin on various evaluation metrics. Besides, the Adaptive Wing loss also helps other heatmap regression tasks.

As robots become more ubiquitous, it is increasingly important for untrained users to be able to interact with them intuitively. In this work, we investigate how people refer to objects in the world during relatively unstructured communication with robots. We collect a corpus of deictic interactions from users describing objects, which we use to train language and gesture models that allow our robot to determine what objects are being indicated. We introduce a temporal extension to state-of-the-art hierarchical matching pursuit features to support gesture understanding, and demonstrate that combining multiple communication modalities more effectively captures user intent than relying on a single type of input. Finally, we present initial interactions with a robot that uses the learned models to follow commands while continuing to learn from user input.

This paper presents an approach for labeling objects in 3D scenes. We introduce HMP3D, a hierarchical sparse coding technique for learning features from 3D point cloud data. HMP3D classifiers are trained using a synthetic dataset of virtual scenes generated using CAD models from an online database. Our scene labeling system combines features learned from raw RGB-D images and 3D point clouds directly, without any hand-designed features, to assign an object label to every 3D point in the scene. Experiments on the RGB-D Scenes Dataset v.2 demonstrate that the proposed approach can be used to label indoor scenes containing both small tabletop objects and large furniture pieces.

Tactile sensing plays an important role in robot grasping and object recognition. In this work, we propose a new descriptor named Spatio-Temporal Hierarchical Matching Pursuit (ST-HMP) that captures properties of a time series of tactile sensor measurements. It is based on the concept of unsupervised hierarchical feature learning realized using sparse coding. The ST-HMP extracts rich spatio-temporal structures from raw tactile data without the need to predefine discriminative data characteristics. We apply it to two different applications: (1) grasp stability assessment and (2) object instance recognition, presenting its universal properties. An extensive evaluation on several synthetic and real datasets collected using the Schunk Dexterous, Schunk Parallel and iCub hands shows that our approach outperforms previously published results by a large margin.

In this paper, we describe a novel approach to construct textured 3D environment models in a hierarchical fashion based on local surface patches. Compared to previous approaches, the hierarchy enables our method to represent the environment with differently sized surface patches. The reconstruction scheme starts at a coarse resolution with large patches and in an iterative fashion uses the reconstruction error to guide the decision as to whether the resolution should be refined. This leads to variable resolution models that represent areas with few variations at low resolution and areas with large variations at high resolution. In addition, we compactly describe local surface attributes via sparse coding based on an overcomplete dictionary. In this way, we additionally exploit similarities in structure and texture, which leads to compact models. We learn the dictionary directly from the input data and independently for every level in the hierarchy in an unsupervised fashion. Practical experiments with large-scale datasets demonstrate that our method compares favorably with two state-of-the-art techniques while being comparable in accuracy.

Identifying objects based on language descriptions is an important capability for robots interacting with people in everyday environments. People naturally use attributes and names to refer to objects of interest. Due to the complexity of indoor environments and the fact that people use various ways to refer to objects, a robot frequently encounters new objects or object names. To deal with such situations, a robot must be able to continuously grow its object knowledge base. In this work we introduce a system that organizes objects and names in a semantic hierarchy. Similarity between name words is learned via a hierarchy embedded vector representation. The hierarchy enables reasoning about unknown objects and names. Novel objects are inserted automatically into the knowledge base, where the exact location in the hierarchy is determined by asking a user questions. The questions are informed by the current hierarchy and the appearance of the object. Experiments demonstrate that the learned representation captures the meaning of names and is helpful for object identification with new names.

In this paper, we describe a novel approach to construct compact colored 3D environment models representing local surface attributes via sparse coding. Our method decomposes a set of colored point clouds into local surface patches and encodes them based on an overcomplete dictionary. Instead of storing the entire point cloud, we store a dictionary, surface patch positions, and a sparse code description of the depth and RGB attributes for every patch. The dictionary is learned in an unsupervised way from surface patches sampled from indoor maps. We show that better dictionaries can be learned by extending the K-SVD method with a binary weighting scheme that ignores undefined surface cells. Through experimental evaluation on real world laser and RGBD datasets we demonstrate that our method produces compact and accurate models. Furthermore, we clearly outperform an existing state of the art method in terms of compactness, accuracy, and computation time. Additionally, we demonstrate that our sparse code descriptions can be utilized for other important tasks such as object detection.

Complex real-world signals, such as images, contain discriminative structures that differ in many aspects including scale, invariance, and data channel. While progress in deep learning shows the importance of learning features through multiple layers, it is equally important to learn features through multiple paths. We propose Multipath Hierarchical Matching Pursuit (M-HMP), a novel feature learning architecture that combines a collection of hierarchical sparse features for image classification to capture multiple aspects of discriminative structures. Our building blocks are MI-KSVD, a codebook learning algorithm that balances the reconstruction error and the mutual incoherence of the codebook, and batch orthogonal matching pursuit (OMP), we apply them recursively at varying layers and scales. The result is a highly discriminative image representation that leads to large improvements to the state-of-the-art on many standard benchmarks, e.g., Caltech-101, Caltech-256, MITScenes, Oxford-IIIT Pet and Caltech-UCSD Bird-200.

Over the last years, the robotics community has made substantial progress in detection and 3D pose estimation of known and unknown objects. However, the question of how to identify objects based on language descriptions has not been investigated in detail. While the computer vision community recently started to investigate the use of attributes for object recognition, these approaches do not consider the task settings typically observed in robotics, where a combination of appearance attributes and object names might be used in referral language to identify specific objects in a scene. In this paper, we introduce an approach for identifying objects based on natural language containing appearance and name attributes. To learn rich RGB-D features needed for attribute classification, we extend recently introduced sparse coding techniques so as to automatically learn attribute-dependent features. We introduce a large data set of attribute descriptions of objects in the RGB-D object dataset. Experiments on this data set demonstrate the strong performance of our approach to language based object identification. We also show that our attribute-dependent features provide significantly better generalization to previously unseen attribute values, thereby enabling more rapid learning of new attribute values.

We introduce SensorSift, a new theoretical scheme for balancing utility and privacy in smart sensor applications. At the heart of our contribution is an algorithm which transforms raw sensor data into a 'sifted' representation which minimizes exposure of user defined private attributes while maximally exposing application-requested public attributes. We envision multiple applications using the same platform, and requesting access to public attributes explicitly not known at the time of the platform creation. Support for future-defined public attributes, while still preserving the defined privacy of the private attributes, is a central challenge that we tackle.

Scene labeling research has mostly focused on outdoor scenes, leaving the harder case of indoor scenes poorly understood. Microsoft Kinect dramatically changed the landscape, showing great potentials for RGB-D perception (color+depth). Our main objective is to empirically understand the promises and challenges of scene labeling with RGB-D. We use the NYU Depth Dataset as collected and analyzed by Silberman and Fergus [30]. For RGB-D features, we adapt the framework of kernel descriptors that converts local similarities (kernels) to patch descriptors. For contextual modeling, we combine two lines of approaches, one using a superpixel MRF, and the other using a segmentation tree. We find that (1) kernel descriptors are very effective in capturing appearance (RGB) and shape (D) similarities; (2) both superpixel MRF and segmentation tree are useful in modeling context; and (3) the key to labeling accuracy is the ability to efficiently train and test with large-scale data. We improve labeling accuracy on the NYU Dataset from 56.6% to 76.1%. We also apply our approach to image-only scene labeling and improve the accuracy on the Stanford Background Dataset from 79.4% to 82.9%.

We propose a view-based approach for labeling objects in 3D scenes reconstructed from RGB-D (color+depth) videos. We utilize sliding window detectors trained from object views to assign class probabilities to pixels in every RGB-D frame. These probabilities are projected into the reconstructed 3D scene and integrated using a voxel representation. We perform efficient inference on a Markov Random Field over the voxels, combining cues from view-based detection and 3D shape, to label the scene. Our detection-based approach produces accurate scene labeling on the RGB-D Scenes Dataset and improves the robustness of object detection.

Finding contours in natural images is a fundamental problem that serves as the basis of many tasks such as image segmentation and object recognition. At the core of contour detection technologies are a set of hand-designed gradient features, used by most existing approaches including the state-of-the-art Global Pb (gPb) operator. In this work, we show that contour detection accuracy can be significantly improved by computing Sparse Code Gradients (SCG), which measure contrast using patch representations automatically learned through sparse coding. We use K-SVD and Orthogonal Matching Pursuit for efficient dictionary learning and encoding, and use multi-scale pooling and power transforms to code oriented local neighborhoods before computing gradients and applying linear SVM. By extracting rich representations from pixels and avoiding collapsing them prematurely, Sparse Code Gradients effectively learn how to measure local contrasts and find contours. We improve the F-measure metric on the BSDS500 benchmark to 0.74 (up from 0.71 of gPb contours). Moreover, our learning approach can easily adapt to novel sensor data such as Kinect-style RGB-D cameras: Sparse Code Gradients on depth images and surface normals lead to promising contour detection using depth and depth+color, as verified on the NYU Depth Dataset. Our work combines the concept of oriented gradients with sparse representation and opens up future possibilities for learning contour detection and segmentation.

Fine-grained recognition refers to a subordinate level of recognition, such are recognizing different species of birds, animals or plants. It differs from recognition of basic categories, such as humans, tables, and computers, in that there are global similarities in shape or structure shared within a category, and the differences are in the details of the object parts. We suggest that the key to identifying the fine-grained differences lies in finding the right alignment of image regions that contain the same object parts. We propose a template model for the purpose, which captures common shape patterns of object parts, as well as the co-occurence relation of the shape patterns. Once the image regions are aligned, extracted features are used for classification. Learning of the template model is efficient, and the recognition results we achieve significantly outperform the state-of-the-art algorithms.

Recognizing possibly thousands of objects is a crucial capability for an autonomous agent to understand and interact with everyday environments. Practical object recognition comes in multiple forms: Is this a coffee mug (category recognition). Is this Alice's coffee mug? (instance recognition). Is the mug with the handle facing left or right? (pose recognition). We present a scalable framework, Object-Pose Tree, which efficiently organizes data into a semantically structured tree. The tree structure enables both scalable training and testing, allowing us to solve recognition over thousands of object poses in near real-time. Moreover, by simultaneously optimizing all three tasks, our approach outperforms standard nearest neighbor and 1-vs-all classifications, with large improvements on pose recognition. We evaluate the proposed technique on a dataset of 300 household objects collected using a Kinect-style 3D camera. Experiments demonstrate that our system achieves robust and efficient object category, instance, and pose recognition on challenging everyday objects.

Material recognition is a fundamental problem in perception that is receiving increasing attention. Following the recent work using Flickr [16, 23], we empirically study material recognition of real-world objects using a rich set of local features. We use the Kernel Descriptor framework [5] and extend the set of descriptors to include material-motivated attributes using variances of gradient orientation and magnitude. Large-Margin Nearest Neighbor learning is used for a 30-fold dimension reduction. We improve the state-of-the-art accuracy on the Flickr dataset [16] from 45 % to 54%. We also introduce two new datasets using ImageNet and macro photos, extensively evaluating our set of features and showing promising connections between material and object recognition.

Kernel descriptors provide a unified way to generate rich visual feature sets by turning pixel attributes into patch-level features, and yield impressive results on many object recognition tasks. However, best results with kernel descriptors are achieved using efficient match kernels in conjunction with nonlinear SVMs, which makes it impractical for large-scale problems. In this paper, we propose hierarchical kernel descriptors that apply kernel descriptors recursively to form image-level features and thus provide a conceptually simple and consistent way to generate image-level features from pixel attributes. More importantly, hierarchical kernel descriptors allow linear SVMs to yield state-of-the-art accuracy while being scalable to large datasets. They can also be naturally extended to extract features over depth images. We evaluate hierarchical kernel descriptors both on the CIFAR10 dataset and the new RGB-D Object Dataset consisting of segmented RGB and depth images of 300 everyday objects.

Over the last decade, the availability of public image repositories and recognition benchmarks has enabled rapid progress in visual object category and instance detection. Today we are witnessing the birth of a new generation of sensing technologies capable of providing high quality synchronized videos of both color and depth, the RGB-D (Kinect-style) camera. With its advanced sensing capabilities and the potential for mass adoption, this technology represents an opportunity to dramatically increase robotic object recognition, manipulation, navigation, and interaction capabilities. In this paper, we introduce a large-scale, hierarchical multi-view object dataset collected using an RGB-D camera. The dataset contains 300 objects organized into 51 categories and has been made publicly available to the research community so as to enable rapid progress based on this promising technology. This paper describes the dataset collection procedure and introduces techniques for RGB-D based object recognition and detection, demonstrating that combining color and depth information substantially improves quality of results.

In this work we address joint object category and instance recognition in the context of RGB-D (depth) cameras. Motivated by local distance learning, where a novel view of an object is compared to individual views of previously seen objects, we define a view-to-object distance where a novel view is compared simultaneously to all views of a previous object. This novel distance is based on a weighted combination of feature differences between views. We show, through jointly learning per-view weights, that this measure leads to superior classification performance on object category and instance recognition. More importantly, the proposed distance allows us to find a sparse solution via Group-Lasso regularization, where a small subset of representative views of an object is identified and used, with the rest discarded. This significantly reduces computational cost without compromising recognition accuracy. We evaluate the proposed technique, Instance Distance Learning (IDL), on the RGB-D Object Dataset, which consists of 300 object instances in 51 everyday categories and about 250,000 views of objects with both RGB color and depth. We empirically compare IDL to several alternative state-of-the-art approaches and also validate the use of visual and shape cues and their combination.

This paper presents Gambit, a custom, mid-cost 6-DoF robot manipulator system that can play physical board games against human opponents in non-idealized environments. Historically, unconstrained robotic manipulation in board games has often proven to be more challenging than the underlying game reasoning, making it an ideal testbed for small-scale manipulation. The Gambit system includes a low-cost Kinect-style visual sensor, a custom manipulator, and state-of-the-art learning algorithms for automatic detection and recognition of the board and objects on it. As a use-case, we describe playing chess quickly and accurately with arbitrary, uninstrumented boards and pieces, demonstrating that Gambit's engineering and design represent a new state-of-the-art in fast, robust tabletop manipulation.

Consumer depth cameras, such as the Microsoft Kinect, are capable of providing frames of dense depth values at real time. One fundamental question in utilizing depth cameras is how to best extract features from depth frames. Motivated by local descriptors on images, in particular kernel descriptors, we develop a set of kernel features on depth images that model size, 3D shape, and depth edges in a single framework. Through extensive experiments on object recognition, we show that (1) our local features capture different aspects of cues from a depth frame/view that complement one another; (2) our kernel features significantly outperform traditional 3D features (e.g. Spin images); and (3) we significantly improve the capabilities of depth and RGB-D (color+depth) recognition, achieving 10–15% improvement in accuracy over the state of the art.

Extracting good representations from images is essential for many computer vision tasks. In this paper, we propose hierarchical matching pursuit (HMP), which builds a feature hierarchy layer-by-layer using an efficient matching pursuit encoder. It includes three modules: batch (tree) orthogonal matching pursuit, spatial pyramid max pooling, and contrast normalization. We investigate the architecture of HMP, and show that all three components are critical for good performance. To speed up the orthogonal matching pursuit, we propose a batch tree orthogonal matching pursuit that is particularly suitable to encode a large number of observations that share the same large dictionary. HMP is scalable and can efficiently handle full-size images. In addition, HMP enables linear support vector machines (SVM) to match the performance of nonlinear SVM while being scalable to large datasets. We compare HMP with many state-of-the-art algorithms including convolutional deep belief networks, SIFT based single layer sparse coding, and kernel based feature learning. HMP consistently yields superior accuracy on three types of image classification problems: object recognition (Caltech-101), scene recognition (MIT-Scene), and static event recognition (UIUC-Sports).

The design of low-level image features is critical for computer vision algorithms. Orientation histograms, such as those in SIFT~\cite{Lowe2004Distinctive} and HOG~\cite{Dalal2005Histograms}, are the most successful and popular features for visual object and scene recognition. We highlight the kernel view of orientation histograms, and show that they are equivalent to a certain type of match kernels over image patches. This novel view allows us to design a family of kernel descriptors which provide a unified and principled framework to turn pixel attributes (gradient, color, local binary pattern, \etc) into compact patch-level features. In particular, we introduce three types of match kernels to measure similarities between image patches, and construct compact low-dimensional kernel descriptors from these match kernels using kernel principal component analysis (KPCA)~\cite{Scholkopf1998Nonlinear}. Kernel descriptors are easy to design and can turn any type of pixel attribute into patch-level features. They outperform carefully tuned and sophisticated features including SIFT and deep belief networks. We report superior performance on standard image classification benchmarks: Scene-15, Caltech-101, CIFAR10 and CIFAR10-ImageNet.

Structured outputs such as multidimensional vectors or graphs are frequently encountered in real world pattern recognition applications such as computer vision, natural language processing or computational biology. This motivates the learning of functional dependencies between spaces with complex, interdependent inputs and outputs, as arising e.g. from images and their corresponding 3d scene representations. In this spirit, we propose a new structured learning method-Structured Output-Associative Regression (SOAR)-that models not only the input-dependency but also the self-dependency of outputs, in order to provide an output re-correlation mechanism that complements the (more standard) input-based regressive prediction. The model is simple but powerful, and, in principle, applicable in conjunction with any existing regression algorithms. SOAR can be kernelized to deal with non-linear problems and learning is efficient via primal/dual formulations not unlike ones used for kernel ridge regression or support vector regression. We demonstrate that the method outperforms weighted nearest neighbor and regression methods for the reconstruction of images of handwritten digits and for 3D human pose estimation from video in the HumanEva benchmark.

Recognizing human action in non-instrumented video is a challenging task not only because of the variability produced by general scene factors like illumination, background, occlusion or intra-class variability, but also because of subtle behavioral patterns among interacting people or between people and objects in images. To improve recognition, a system may need to use not only low-level spatio-temporal video correlations but also relational descriptors between people and objects in the scene. In this paper we present contextual scene descriptors and Bayesian multiple kernel learning methods for recognizing human action in complex non-instrumented video. Our contribution is threefold: (1) we introduce bag-of-detector scene descriptors that encode presence/absence and structural relations between object parts; (2) we derive a novel Bayesian classification method based on Gaussian processes with multiple kernel covariance functions (MKGPC), in order to automatically select and weight multiple features, both low-level and high-level, out of a large collection, in a principled way, and (3) perform large scale evaluation using a variety of features on the KTH and a recently introduced, challenging, Hollywood movie dataset. On the KTH dataset, we obtain 94.1% accuracy, the best result reported to date. On the Hollywood dataset we obtain promising results in several action classes using fewer descriptors and about 9.1% improvement in a previous benchmark test.

We present an integrated model for visual object localization and continuous state estimation in a discriminative structured prediction framework. While existing discriminative `prediction through time' methods have showed remarkable versatility for visual reconstruction and tracking problems, they tend to assume that the input is known (or the object is segmented) a condition that can rarely be accommodated in images of real scenes. Our structural Support Vector Machine (structSVM) framework offers an end-to-end training and inference framework that overcomes these limitations by consistently searching both in the space of possible inputs (effectively an efficient form of object localization) and in the space of possible structured outputs, given those inputs. We demonstrate the potential of this methodology for 3d human pose reconstruction in monocular images both in the HumanEva benchmark, where 3d ground truth is available, and qualitatively, in un-instrumented images of real scenes.

In visual recognition, the images are frequently modeled as sets of local features (bags). We show that bag of words, a common method to handle such cases, can be viewed as a special match kernel, which counts 1 if two local features fall into the same regions partitioned by visual words and 0 otherwise. Despite its simplicity, this quantization is too coarse. It is, therefore, appealing to design match kernels that more accurately measure the similarity between local features. However, it is impractical to use such kernels on large datasets due to their significant computational cost. To address this problem, we propose an efficient match kernel (EMK), which maps local features to a low dimensional feature space, average the resulting feature vectors to form a set-level feature, then apply a linear classifier. The local feature maps are learned so that their inner products preserve, to the best possible, the values of the specified kernel function. EMK is linear both in the number of images and in the number of local features. We demonstrate that EMK is extremely efficient and achieves the current state of the art performance on three difficult real world datasets: Scene-15, Caltech-101 and Caltech-256.

Conditional random fields (CRF) are quite successful on sequence labeling tasks such as natural language processing and biological sequence analysis. CRF models use linear potential functions to represent the relationship between input features and outputs. However, in many real-world applications such as protein structure prediction and handwriting recognition, the relationship between input features and outputs is highly complex and nonlinear, which cannot be accurately modeled by a linear function. To model the nonlinear relationship between input features and outputs we propose Conditional Neural Fields (CNF), a new conditional probabilistic graphical model for sequence labeling. Our CNF model extends CRF by adding one (or possibly several) middle layer between input features and outputs. The middle layer consists of a number of hidden parameterized gates, each acting as a local neural network node or feature extractor to capture the nonlinear relationship between input features and outputs. Therefore, conceptually this CNF model is much more expressive than the linear CRF model. To better control the complexity of the CNF model, we also present a hyperparameter optimization procedure within the evidence framework. Experiments on two widely-used benchmarks indicate that this CNF model performs significantly better than a number of popular methods. In particular, our CNF model is the best among about ten machine learning methods for protein secondary tructure prediction and also among a few of the best methods for handwriting recognition.

The potential success of discriminative learning approaches to 3D reconstruction relies on the ability to efficiently train predictive algorithms using sufficiently many examples that are representative of the typical configurations encountered in the application domain. Recent research indicates that sparse conditional Bayesian mixture of experts (cMoE) models (e.g. BME (Sminchisescu et al., 2005)) are adequate modeling tools that not only provide contextual 3D predictions for problems like human pose reconstruction, but can also represent multiple interpretations that result from depth ambiguities or occlusion. However, training conditional predictors requires sophisticated double-loop algorithms that scale unfavorably with the input dimension and the training set size, thus limiting their usage to 10,000 examples of less, so far. In this paper we present large-scale algorithms, referred to as fBME, that combine forward feature selection and bound optimization in order to train probabilistic, BME models, with one order of magnitude more data (100,000 examples and up) and more than one order of magnitude faster. We present several large scale experiments, including monocular evaluation on the HumanEva dataset (Sigal and Black, 2006), demonstrating how the proposed methods overcome the scaling limitations of existing ones.

Abstract Nondominated Neighbor Immune Algorithm (NNIA) is proposed for multiobjective optimization by using a novel nondominated neighbor-based selection technique, an immune inspired operator, two heuristic search operators, and elitism. The unique selection technique of NNIA only selects minority isolated nondominated individuals in the population. The selected individuals are then cloned proportionally to their crowding-distance values before heuristic search. By using the nondominated neighbor-based selection and proportional cloning, NNIA pays more attention to the less-crowded regions of the current trade-off front. We compare NNIA with NSGA-II, SPEA2, PESA-II, and MISA in solving five DTLZ problems, five ZDT problems, and three low-dimensional problems. The statistical analysis based on three performance metrics including the coverage of two sets, the convergence metric, and the spacing, show that the unique selection method is effective, and NNIA is an effective algorithm for solving multiobjective optimization problems. The empirical study on NNIA's scalability with respect to the number of objectives shows that the new algorithm scales well along the number of objectives.

Spectral clustering (SC) has been used with success in the field of computer vision for data clustering. In this paper, a new algorithm named SC ensemble (SCE) is proposed for the segmentation of synthetic aperture radar (SAR) images. The gray-level cooccurrence matrix-based statistic features and the energy features from the undecimated wavelet decomposition extracted for each pixel being the input, our algorithm performs segmentation by combining multiple SC results as opposed to using outcomes of a single clustering process in the existing literature. The random subspace, random scaling parameter, and Nystrom approximation for component SC are applied to construct the SCE. This technique provides necessary diversity as well as high quality of component learners for an efficient ensemble. It also overcomes the shortcomings faced by the SC, such as the selection of scaling parameter, and the instability resulted from the Nystrom approximation method in image segmentation. Experimental results show that the proposed method is effective for SAR image segmentation and insensitive to the scaling parameter.

Hard-margin support vector machines (HM-SVMs) suffer from getting overfitting in the presence of noise. Soft-margin SVMs deal with this problem by introducing a regularization term and obtain a state-of-the-art performance. However, this disposal leads to a relatively high computational cost. In this paper, an alternative method, greedy stagewise algorithm for SVMs, named GS-SVMs, is presented to cope with the overfitting of HM-SVMs without employing the regularization term. The most attractive property of GS-SVMs is that its computational complexity in the worst case only scales quadratically with the size of training samples. Experiments on the large data sets with up to 400,000 training samples demonstrate that GS-SVMs can be faster than LIBSVM 2.83 without sacrificing the accuracy. Finally, we employ statistical learning theory to analyze the empirical results, which shows that the success of GS-SVMs lies in that its early stopping rule can act as an implicit regularization term.

Some algorithms in the primal have been recently proposed for training support vector machines. This letter follows those studies and develops a recursive finite Newton algorithm (IHLF-SVR-RFN) for training nonlinear support vector regression. The insensitive Huber loss function and the computation of the Newton step are discussed in detail. Comparisons with LIBSVM 2.82 show that the proposed algorithm gives promising results.

The efficiency of sequential minimal optimization (SMO) depends strongly on the working set selection. This letter shows how the improvement of SMO in each iteration, named the functional gain (FG), is used to select the working set for least squares support vector machine (LS-SVM). We prove the convergence of the proposed method and give some theoretical support for its performance. Empirical comparisons demonstrate that our method is superior to the maximum violating pair (MVP) working set selection.

In this paper, we present two fast sparse approximation schemes for least squares support vector machine (LS-SVM), named FSALS-SVM and PFSALS-SVM, to overcome the limitation of LS-SVM that it is not applicable to large data sets and to improve test speed. FSALS-SVM iteratively builds the decision function by adding one basis function from a kernel-based dictionary at one time. The process is terminated by using a flexible and stable epsilon insensitive stopping criterion. A probabilistic speedup scheme is employed to further improve the speed of FSALS-SVM and the resulting classifier is named PFSALS-SVM. Our algorithms are of two compelling features: low complexity and sparse solution. Experiments on benchmark data sets show that our algorithms obtain sparse classifiers at a rather low cost without sacrificing the generalization performance.

Kernel fisher discriminant analysis (KFD) is a successful approach to classification. It is well known that the key challenge in KFD lies in the selection of free parameters such as kernel parameters and regularization parameters. Here we focus on the feature-scaling kernel where each feature individually associates with a scaling factor. A novel algorithm, named FS-KFD, is developed to tune the scaling factors and regularization parameters for the feature-scaling kernel. The proposed algorithm is based on optimizing the smooth leave-one-out error via a gradient-descent method and has been demonstrated to be computationally feasible. FS-KFD is motivated by the following two fundamental facts: the leave-one-out error of KFD can be expressed in closed form and the step function can be approximated by a sigmoid function. Empirical comparisons on artificial and benchmark data sets suggest that FS-KFD improves KFD in terms of classification accuracy.