Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a hierarchical plug-and-play pruning-and-recovering framework, calledHierarchicalHourglassTokenizer (H2OT), for efficient transformer-based 3D human pose estimation from videos. H2OT begins with progressively pruning pose tokens of redundant frames and ends with recovering full-length sequences, resulting in a few pose tokens in the intermediate transformer blocks and thus improving the model efficiency. It works with two key modules, namely, a Token Pruning Module (TPM) and a Token Recovering Module (TRM). TPM dynamically selects a few representative tokens to eliminate the redundancy of video frames, while TRM restores the detailed spatio-temporal information based on the selected tokens, thereby expanding the network output to the original full-length temporal resolution for fast inference. Our method is general-purpose: it can be easily incorporated into common VPT models on bothseq2seqandseq2framepipelines while effectively accommodating different token pruning and recovery strategies. In addition, our H2OT reveals that maintaining the full pose sequence is unnecessary, and a few pose tokens of representative frames can achieve both high efficiency and estimation accuracy. Extensive experiments on multiple benchmark datasets demonstrate both the effectiveness and efficiency of the proposed method. Code and models are available athttps://github.com/NationalGAILab/HoT.

Although data-driven methods have achieved success in 3D human pose estimation, they often suffer from domain gaps and exhibit limited generalization. In contrast, optimization-based methods excel in fine-tuning for specific cases but are generally inferior to data-driven methods in overall performance. We observe that previous optimization-based methods commonly rely on projection constraint, which only ensures alignment in 2D space, potentially leading to the overfitting problem. To address this, we propose an Uncertainty-Aware testing-time Optimization (UAO) framework, which keeps the prior information of pre-trained model and alleviates the overfitting problem using the uncertainty of joints. Specifically, during the training phase, we design an effective 2D-to-3D network for estimating the corresponding 3D pose while quantifying the uncertainty of each 3D joint. For optimization during testing, the proposed optimization framework freezes the pre-trained model and optimizes only a latent state. Projection loss is then employed to ensure the generated poses are well aligned in 2D space for high-quality optimization. Furthermore, we utilize the uncertainty of each joint to determine how much each joint is allowed for optimization. The effectiveness and superiority of the proposed framework are validated through extensive experiments on challenging datasets: Human3.6M, MPI-INF-3DHP, and 3DPW. Notably, our approach outperforms the previous best result by a large margin of 5.5% on Human3.6M.

Recent multi-frame lifting methods have dominated the 3D human pose estimation. However, previous methods ignore the intricate dependence within the 2D pose sequence and learn single temporal correlation. To alleviate this limitation, we propose TCPFormer, which leverages an implicit pose proxy as an intermediate representation. Each proxy within the implicit pose proxy can build one temporal correlation therefore helping us learn a more comprehensive temporal correlation of human motion. Specifically, our method consists of three key components: Proxy Update Module (PUM), Proxy Invocation Module (PIM), and Proxy Attention Module (PAM). PUM first uses pose features to update the implicit pose proxy, enabling it to store representative information from the pose sequence. PIM then invocates and integrates the pose proxy with the pose sequence to enhance the motion semantics of each pose. Finally, PAM leverages the above mapping between the pose sequence and pose proxy to enhance the temporal correlation of the whole pose sequence. Experiments on the Human3.6M and MPI-INF-3DHP datasets demonstrate that our proposed TCPFormer outperforms the previous state-of-the-art methods.

Recently, transformer-based methods have been introduced to estimate 3D human pose from multiple views by aggregating the spatial-temporal information of human joints to achieve the lifting of 2D to 3D. However, previous approaches cannot model the inter-frame correspondence of each view's joint individually, nor can they directly consider all view interactions at each time, leading to insufficient learning of multi-view associations. To address this issue, we propose a Spatial-View-Temporal transformer (SVTformer) to decouple spatial-view-temporal information in sequential order for correlation learning and model dependencies between them in a local-to-global manner. SVTformer includes an attended Spatial-View-Temporal (SVT) patch embedding to attentively capture the local features of the input poses and stacked SVT encoders to extract global spatial-view-temporal dependencies progressively. Specifically, SVT encoders perform three reconstructions sequentially to attended features with the learning through view decoupling for temporal-enhanced spatial correlation, temporal decoupling for spatial-enhanced view correlation, and another view decoupling for spatial-enhanced temporal relationship. This decoupling-coupling-decoupling multi-view scheme enables us to alternatively model the inter-joint spatial relationships, cross-view dependencies, and temporal motion associations. We evaluate the proposed SVTformer on three popular 3D HPE datasets, and it yields state-of-the-art performance. It effectively deals with ill-posed problems and enhances the accuracy of 3D human pose estimation.

The integration of point and voxel representations is becoming more common in Light Detection and Ranging (LiDAR)-based 3D object detection. However, existing fusion strategies suffer from ineffective semantic alignment and contextual information loss, while relying solely on point features within regions of interest leads to geometric detail degradation and limited local–global feature integration. To tackle these challenges, we propose the Point-Voxel Attention Fusion Network (PVAFN), a novel two-stage 3D object detector that introduces a point-voxel attention fusion module based on dual-gated cross-modal interaction and a multi-pooling strategy based on density-space awareness. During the feature extraction and fusion stage, a dual-gated hierarchical attention mechanism is proposed to dynamically fuse three heterogeneous modalities—keypoint-based geometric details, voxel-wise local regularity, and Bird’s-Eye-View (BEV)-level global semantics—through learnable gating functions. In the refinement stage, a density-spatial-aware multi-pooling enhancement module is designed to synergize density-aware cluster pooling and multi-scale spatial-aware pyramid pooling, efficiently capturing key geometric details and fine-grained shape structures. This design enhances the integration of local and global features while enabling adaptive multi-scale context modeling and spatially sensitive feature aggregation. Extensive experiments on the KITTI and Waymo benchmark datasets demonstrate that PVAFN achieves promising detection accuracy in 3D mean Average Precision. • PVAFN: A novel network for 3D object detection, fusing keypoint, voxel, and BEV features dynamically. • Stage-I: Dual-gated hierarchical attention fusion for bidirectional point-voxel feature calibration. • Stage-II: Density-spatial-aware multi-pooling module enhances local and global geometric perception. • SOTA Performance: PVAFN achieves highest AP on KITTI and Waymo benchmarks for autonomous driving.

The widespread application of 3D human pose estimation (HPE) is limited by resource-constrained edge devices like Jetson Nano, requiring more efficient models. A key approach to enhancing efficiency involves designing networks based on the structural characteristics of input data. However, effectively utilizing the structural priors in human skeletal inputs remains challenging. To address this, we leverage both explicit and implicit spatio-temporal priors of the human body through innovative model design and a pre-training proxy task. First, we propose a Nano Human Topology Network (NanoHTNet), a tiny 3D HPE network with stacked Hierarchical Mixers to capture explicit features. Specifically, the spatial Hierarchical Mixer efficiently learns the human physical topology across multiple semantic levels, while the temporal Hierarchical Mixer with discrete cosine transform and low-pass filtering captures local instantaneous movements and global action coherence. Moreover, Efficient Temporal-Spatial Tokenization (ETST) is introduced to enhance spatio-temporal interaction and reduce computational complexity significantly. Second, PoseCLR is proposed as a general pre-training method based on contrastive learning for 3D HPE, aimed at extracting implicit representations of human topology. By aligning 2D poses from diverse viewpoints in the proxy task, PoseCLR aids 3D HPE encoders like NanoHTNet in more effectively capturing the high-dimensional features of the human body, leading to further performance improvements. Extensive experiments verify that NanoHTNet with PoseCLR outperforms other state-of-the-art methods in efficiency, making it ideal for deployment on edge devices like the Jetson Nano. Code and models are available at https://github.com/vefalun/NanoHTNet.

Regression-based 3D human pose and shape estimation often fall into one of two different paradigms. Parametric approaches, which regress the parameters of a human body model, tend to produce physically plausible but image-mesh misalignment results. In contrast, non-parametric approaches directly regress human mesh vertices, resulting in pixel-aligned but unreasonable predictions. In this paper, we consider these two paradigms together for a better overall estimation. To this end, we propose a novel HYbrid REgressor (HYRE) that greatly benefits from the joint learning of both paradigms. The core of our HYRE is a hybrid intermediary across paradigms that provides complementary clues to each paradigm at the shared feature level and fuses their results at the part-based decision level, thereby bridging the gap between the two. We demonstrate the effectiveness of the proposed method through both quantitative and qualitative experimental analyses, resulting in improvements for each approach and ultimately leading to better hybrid results. Our experiments show that HYRE outperforms previous methods on challenging 3D human pose and shape benchmarks.

The lifting-based methods have dominated monocular 3D human pose estimation by leveraging detected 2D poses as intermediate representations. The 2D component of the final 3D human pose benefits from the detected 2D poses, whereas its depth counterpart must be estimated from scratch. The lifting-based methods encode the detected 2D pose and unknown depth in an entangled feature space, explicitly introducing depth uncertainty to the detected 2D pose, thereby limiting overall estimation accuracy. This work reveals that the depth representation is pivotal for the estimation process. Specifically, when depth is in an initial, completely unknown state, jointly encoding depth features with 2D pose features is detrimental to the estimation process. In contrast, when depth is initially refined to a more dependable state via network-based estimation, encoding it together with 2D pose information is beneficial. To address this limitation, we present a Mixture-of-Experts network for monocular 3D pose estimation named PoseMoE. Our approach introduces: 1) A mixture-of-experts network where specialized expert modules refine the well-detected 2D pose features and learn the depth features. This mixture-of-experts design disentangles the feature encoding process for 2D pose and depth, therefore reducing the explicit influence of uncertain depth features on 2D pose features. 2) A cross-expert knowledge aggregation module is proposed to aggregate cross-expert spatio-temporal contextual information. This step enhances features through bidirectional mapping between 2D pose and depth. Extensive experiments show that our proposed PoseMoE outperforms the conventional lifting-based methods on three widely used datasets: Human3.6M, MPI-INF-3DHP, and 3DPW.

Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a plug-and-play pruning-and-recovering framework, called Hourglass Tokenizer (HoT), for efficient transformer-based 3D human pose estimation from videos. Our HoT begins with pruning pose tokens of re-dundant frames and ends with recovering full-length tokens, resulting in a few pose tokens in the intermediate transformer blocks and thus improving the model efficiency. To effectively achieve this, we propose a token pruning cluster (TPC) that dynamically selects a few representative tokens with high semantic diversity while eliminating the redundancy of video frames. In addition, we develop a token recovering attention (TRA) to restore the detailed spatio-temporal information based on the selected tokens, thereby expanding the network output to the original full-length temporal resolution for fast inference. Extensive experiments on two benchmark datasets (i.e., Human3.6M and MPI-INF-3DHP) demonstrate that our method can achieve both high efficiency and estimation accuracy compared to the original VPT models. For instance, applying to MotionBERT and MixSTE on Hu-man3.6M, our HoT can save nearly 50% FLOPs without sacrificing accuracy and nearly 40% FLOPs with only 0.2% accuracy drop, respectively. Code and models are available at https://github.com/NationalGAILab/HoT.

Human Mesh Reconstruction (HMR) from monocular video plays an important role in human-robot interaction and collaboration. However, existing video-based human mesh reconstruction methods face a trade-off between accurate reconstruction and smooth motion. These methods design networks based on either RNNs or attention mechanisms to extract local temporal correlations or global temporal dependencies, but the lack of complementary long-term information and local details limits their performance. To address this problem, we propose a Dual-branch Graph Transformer network for 3D human mesh Reconstruction from video, named DGTR. DGTR employs a dual-branch network including a Global Motion Attention (GMA) branch and a Local Details Refine (LDR) branch to par-allelly extract long-term dependencies and local crucial information, helping model global human motion and local human details (e.g., local motion, tiny movement). Specifically, GMA utilizes a global transformer to model long-term human motion. LDR combines modulated graph convolutional networks and the transformer framework to aggregate local information in adjacent frames and extract crucial information of human details. Experiments demonstrate that our DGTR outperforms state-of-the-art video-based methods in reconstruction accuracy and maintains competitive motion smoothness. Moreover, DGTR utilizes fewer parameters and FLOPs, which validate the effectiveness and efficiency of the proposed DGTR. Code is publicly available at https://github.com/TangTao-PKU/DGTR.

Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image features lack sufficient spatial information about the human body and contain various noises (e.g., background, lighting, and clothing), which often results in inaccurate pose and inconsistent motion. Inspired by the rapid advance in human pose estimation, we discover that compared to image features, skeletons inherently contain accurate human pose and motion. Therefore, we propose a novel semiAnalytical Regressor using disenTangled Skeletal representations for human mesh recovery from videos, called ARTS. Specifically, a skeleton estimation and disentanglement module is proposed to estimate the 3D skeletons from a video and decouple them into disentangled skeletal representations (i.e., joint position, bone length, and human motion). Then, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model. The regressor consists of three modules: Temporal Inverse Kinematics (TIK), Bone-guided Shape Fitting (BSF), and Motion-Centric Refinement (MCR). TIK utilizes joint position to estimate initial pose parameters and BSF leverages bone length to regress bone-aligned shape parameters. Finally, MCR combines human motion representation with image features to refine the initial human model parameters. Extensive experiments demonstrate that our ARTS surpasses existing state-of-the-art video-based methods in both per-frame accuracy and temporal consistency on popular benchmarks: 3DPW, MPI-INF-3DHP, and Human3.6M. Code is available at https://github.com/TangTao-PKU/ARTS.

Occluded person re-identification is a challenging problem due to the destruction of occluders in different camera views. Most existing paradigms focus on visible human body parts through some external models to reduce noise interference. However, the feature misalignment problem caused by discarded occlusions negatively affects the performance of the network. Different from most previous works that discard the occluded regions, we present Feature Completion Transformer (FCFormer) that reduces noise interference and complements missing features in occluded parts. Specifically, Occlusion Instance Augmentation is proposed to simulate real and diverse occlusion situations on the holistic image, which enlarges the occlusion samples in the training set and forms aligned occluded-holistic pairs. To reduce the interference of noise, a two-stream architecture is proposed to learn pairwise discriminative features from aligned image pairs, while obtaining self-aligned occluded-holistic feature level sample-label pairs without additional auxiliary models. To complement the features of occluded regions, a Feature Completion Decoder is designed to aggregate possible information from self-generated occluded features in a self-supervised manner. Further, in order to correlate the completion features with identity information, Feature Completion Consistency loss is introduced to enforce the distribution of the generated completion features to be consistent with the real holistic feature distribution. In addition, we propose the Cross Hard Triplet loss to further bridge the gap between completion features and extracting features under the same ID. Extensive experiments over five challenging datasets demonstrate that the proposed FCFormer achieves superior performance and outperforms the state-of-theart methods by significant margins on Occluded-Duke dataset.

One main challenge of visible-infrared person re-identification (VI Re-ID) lies in the large style discrepancy between the heterogeneous data. We present a STyle-Agnostic Representation learning (STAR) framework that bridges the modality gaps at both data and feature levels in a progressive manner. At the data level, we present Cross Modality Blending (CMB), a powerful and parameter-free data augmentation scheme that smoothly synthesizes intermediate modalities by conducting identity-preserving patch exchange and smooth cross-modality blending. At the feature level, we explore the inter-modality feature alignment problem from a new perspective of the style-related feature statistics. Specifically, we design a plug-and-play Adaptive Style Normalization (ASN) module to discard the intrinsic style distractors without losing discriminative content via dual-level adaptive distribution normalization and discriminability compensation. Moreover, considering that an appropriate modality intermediary can convey relevant information on the inter-modality distribution shift, we propose Reciprocal Modality Bridging Learning (RMBL) to better steer the modality bridging process. Two lightweight modality transformation modules are designed in RMBL to model an appropriate intermediate space by manipulating high-order statistics under our shortest distance constraint. Meanwhile, intermediary-guided distribution alignment is reciprocally conducted to align heterogeneous features to the modality intermediary. Experiments on VI Re-ID benchmarks demonstrate the superiority and flexibility of STAR over state-of-the-art methods.

3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs. Inspired by the backtracking mechanism in automatic control systems, we design an Intra-Part Constraint module that utilizes the parent nodes as the reference to build topological constraints for end joints at the part level. Further considering the hierarchy of the human topology, joint-level and body-level dependencies are captured via graph convolutional networks and self-attentions, respectively. Based on these designs, we propose a novel Human Topology aware Network (HTNet), which adopts a channel-split progressive strategy to sequentially learn the structural priors of the human topology from multiple semantic levels: joint, part, and body. Extensive experiments show that the proposed method improves the estimation accuracy by 18.7% on the end joints of limbs and achieves state-of-the-art results on Human3.6M and MPI-INF-3DHP datasets. Code is available at https://github.com/vefalun/HTNet.

Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations. To address this issue, we propose a novel Interweaved Graph and Attention Network (IGANet) that allows bidirectional communications between graph convolutional networks (GCNs) and attentions. Specifically, we introduce an IGA module, where attentions are provided with local information from GCNs and GCNs are injected with global information from attentions. Additionally, we design a simple yet effective U-shaped multi-layer perceptron (uMLP), which can capture multi-granularity information for body joints. Extensive experiments on two popular benchmark datasets (i.e. Human3.6M and MPI-INF-3DHP) are conducted to evaluate our proposed method. The results show that IGANet achieves state-of-the-art performance on both datasets. Code is available at https://github.com/xiu-cs/IGANet.

3D human mesh recovery from a 2D pose plays an important role in various applications. However, it is hard for existing methods to simultaneously capture the multiple relations during the evolution from skeleton to mesh, including joint-joint, joint-vertex and vertex-vertex relations, which often leads to implausible results. To address this issue, we propose a novel solution, called GATOR, that contains an encoder of Graph-Aware Transformer (GAT) and a decoder with Motion-Disentangled Regression (MDR) to explore these multiple relations. Specifically, GAT combines a GCN and a graph-aware self-attention in parallel to capture physical and hidden joint-joint relations. Furthermore, MDR models joint-vertex and vertex-vertex interactions to explore joint and vertex relations. Based on the clustering characteristics of vertex offset fields, MDR regresses the vertices by composing the predicted base motions. Extensive experiments show that GATOR achieves state-of-the-art performance on two challenging benchmarks. Code is available at https://github.com/kasvii/GATOR.

Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging. Existing video-based methods generally recover human mesh by estimating the complex pose and shape parameters from coupled image features, whose high complexity and low representation ability often result in inconsistent pose motion and limited shape patterns. To alleviate this issue, we introduce 3D pose as the intermediary and propose a Pose and Mesh Co-Evolution network (PMCE) that decouples this task into two parts: 1) video-based 3D human pose estimation and 2) mesh vertices regression from the estimated 3D pose and temporal image feature. Specifically, we propose a two-stream encoder that estimates mid-frame 3D pose and extracts a temporal image feature from the input image sequence. In addition, we design a co-evolution decoder that performs pose and mesh interactions with the image-guided Adaptive Layer Normalization (AdaLN) to make pose and mesh fit the human body shape. Extensive experiments demonstrate that the proposed PMCE outperforms previous state-of-the-art methods in terms of both per-frame accuracy and temporal consistency on three benchmark datasets: 3DPW, Human3.6M, and MPI-INF-3DHP. Our code is available at https://github.com/kasvii/PMCE.

Despite significant progress, estimating 3D human poses from monocular videos remains a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions ( i.e. , hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, we introduce a one-to-many-to-one three-stage framework: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that the proposed method achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. The code and models are available at https://github.com/Vegetebird/MHFormer .

Although monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view information is a practical way to achieve absolute 3D human pose estimation. In this paper, we propose a simple yet effective pipeline for weakly-supervised cross-view 3D human pose estimation. By only using two camera views, our method can achieve state-of-the-art performance in a weakly-supervised manner, requiring no 3D ground truth but only 2D annotations. Specifically, our method contains two steps: triangulation and refinement. First, given the 2D keypoints that can be obtained through any classic 2D detection methods, triangulation is performed across two views to lift the 2D keypoints into coarse 3D poses. Then, a novel cross-view U-shaped graph convolutional network (CV-UGCN), which can explore the spatial configurations and cross-view correlations, is designed to refine the coarse 3D poses. In particular, the refinement progress is achieved through weakly-supervised learning, in which geometric and structure-aware consistency checks are performed. We evaluate our method on the standard benchmark dataset, Human3.6M. The Mean Per Joint Position Error on the benchmark dataset is 27.4 mm, which outperforms existing state-of-the-art methods remarkably (27.4 mm vs 30.2 mm).

Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative representations for generating one 3D pose. To this end, we propose an improved Transformer-based architecture, called Strided Transformer, which simply and effectively lifts a long sequence of 2D joint locations to a single 3D pose. Specifically, a Vanilla Transformer Encoder (VTE) is adopted to model long-range dependencies of 2D pose sequences. To reduce the redundancy of the sequence, fully-connected layers in the feed-forward network of VTE are replaced with strided convolutions to progressively shrink the sequence length and aggregate information from local contexts. The modified VTE is termed as Strided Transformer Encoder (STE), which is built upon the outputs of VTE. STE not only effectively aggregates long-range information to a single-vector representation in a hierarchical global and local fashion, but also significantly reduces the computation cost. Furthermore, a full-to-single supervision scheme is designed at both full sequence and single target frame scales applied to the outputs of VTE and STE, respectively. This scheme imposes extra temporal smoothness constraints in conjunction with the single target frame supervision and hence helps produce smoother and more accurate 3D poses. The proposed Strided Transformer is evaluated on two challenging benchmark datasets, Human3.6 M and HumanEva-I, and achieves state-of-the-art results with fewer parameters. Code and models are available athttps://github.com/Vegetebird/StridedTransformer-Pose3D.

Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are available at https://github.com/Vegetebird/MHFormer.

The fusion of audio and visual modalities is an important stage of audio-visual speech recognition (AVSR), which is generally approached through feature fusion or decision fusion. Feature fusion can exploit the covariations between features from different modalities effectively, whereas decision fusion shows the robustness of capturing an optimal combination of multimodality. In this work, to take full advantage of the complementarity of the two fusion strategies and address the challenge of inherent ambiguity in noisy environments, we propose a novel hybrid fusion based AVSR method with residual networks and Bidirectional Gated Recurrent Unit (BGRU), which is able to distinguish homophones in both clean and noisy conditions. Specifically, a simple yet effective audio-visual encoder is used to map audio and visual features into a shared latent space to capture more discriminative multi-modal feature and find the internal correlation between spatial-temporal information for different modalities. Furthermore, a decision fusion module is designed to get final predictions in order to robustly utilize the reliability measures of audio-visual information. Finally, we introduce a combined loss, which shows its noise-robustness in learning the joint representation across various modalities. Experimental results on the largest publicly available dataset (LRW) demonstrate the robustness of the proposed method under various noisy conditions.