Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number of regions, this paradigm struggles with contemporary documents, which exhibit diverse element counts and increasingly complex layouts. To address challenges posed by modern documents, we present HybriDLA, a novel generative framework that unifies diffusion and autoregressive decoding within a single layer. The diffusion component iteratively refines bounding-box hypotheses, whereas the autoregressive component injects semantic and contextual awareness, enabling precise region prediction even in highly varied layouts. To further enhance detection quality, we design a multi-scale feature-fusion encoder that captures both fine-grained and high-level visual cues. This architecture elevates performance to 83.5% mean Average Precision (mAP). Extensive experiments on the DocLayNet and M6Doc benchmarks demonstrate that HybriDLA sets a state-of-the-art performance, outperforming previous approaches.

When reading a document, glancing at the spatial layout of a document is an initial step to understand it roughly. Traditional document layout analysis (DLA) methods, however, offer only a superficial parsing of documents, focusing on basic instance detection and often failing to capture the nuanced spatial and logical relationships between instances. These limitations hinder DLA-based models from achieving a gradually deeper comprehension akin to human reading. In this work, we propose a novel graph-based Document Structure Analysis (gDSA) task. This task requires that model not only detects document elements but also generates spatial and logical relations in form of a graph structure, allowing to understand documents in a holistic and intuitive manner. For this new task, we construct a relation graph-based document structure analysis dataset(GraphDoc) with 80K document images and 4.13M relation annotations, enabling training models to complete multiple tasks like reading order, hierarchical structures analysis, and complex inter-element relationship inference. Furthermore, a document relation graph generator (DRGG) is proposed to address the gDSA task, which achieves performance with 57.6% at $mAP_g$@$0.5$ for a strong benchmark baseline on this novel task and dataset. We hope this graphical representation of document structure can mark an innovative advancement in document structure analysis and understanding. The new dataset and code will be made publicly available.

Brain decoding aims to reconstruct visual perception of human subject from fMRI signals, which is crucial for understanding brain’s perception mechanisms. Existing methods are confined to the single-subject paradigm due to substantial brain variability, which leads to weak generalization across individuals and incurs high training costs, exacerbated by limited availability of fMRI data. To address these challenges, we propose MindAligner, an explicit functional alignment framework for cross-subject brain decoding from limited fMRI data. The proposed MindAligner enjoys several merits. First, we learn a Brain Transfer Matrix (BTM) that projects the brain signals of an arbitrary new subject to one of the known subjects, enabling seamless use of pre-trained decoding models. Second, to facilitate reliable BTM learning, a Brain Functional Alignment module is proposed to perform soft cross-subject brain alignment under different visual stimuli with a multi-level brain alignment loss, uncovering fine-grained functional correspondences with high interpretability. Experiments indicate that MindAligner not only outperforms existing methods in visual decoding under data-limited conditions, but also provides valuable neuroscience insights in cross-subject functional analysis. The code will be made publicly available.

To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions—a common yet often overlooked scenario in existing self-supervised skeleton-based action recognition methods. In this work, we propose IosPSTL, a simple and effective self-supervised learning framework designed to handle occlusions. IosPSTL combines a cluster-agnostic KNN imputer with an Occluded Partial Spatio-Temporal Learning (OPSTL) strategy. First, we pre-train the model on occluded skeleton sequences. Then, we introduce a cluster-agnostic KNN imputer that performs semantic grouping using k-means clustering on sequence embeddings. It imputes missing skeleton data by applying K-Nearest Neighbors in the latent space, leveraging nearby sample representations to restore occluded joints. This imputation generates more complete skeleton sequences, which significantly benefits downstream self-supervised models. To further enhance learning, the OPSTL module incorporates Adaptive Spatial Masking (ASM) to make better use of intact, high-quality skeleton sequences during training. Our method achieves state-of-the-art performance on the occluded versions of the NTU-60 and NTU-120 datasets, demonstrating its robustness and effectiveness under challenging conditions. Code is available at https://github.com/cyfml/OPSTL.

Semantic scene understanding in bird-eye view (BEV) plays a crucial role in autonomous driving. A common approach to generating BEV maps from LiDAR point-cloud data involves constructing a pillar-level representation by projecting 3D point clouds onto a 2D plane. This process partially discards spatial geometric information, and produces sparse semantic maps. However, downstream tasks (e.g., trajectory planning and prediction), typically require dense grid-like semantic BEV maps rather than sparse segmentation outputs. To bridge this gap, we propose PointDenseBEV, an end-to-end, distribution-aware feature fusion framework. It takes as input sparse LiDAR point clouds and directly generates dense semantic BEV maps. Spatial geometric information and temporal context are embedded as auxiliary semantic cues within the BEV grid representation to enhance semantic density. Extensive experiments on the SemanticKITTI dataset demonstrate that our method achieves competitive performance compared to existing approaches.

We propose VISO-Grasp, a novel vision-language-informed system designed to systematically address visibility constraints for grasping in severely occluded environments. By leveraging Foundation Models (FMs) for spatial reasoning and active view planning, our framework constructs and updates an instance-centric representation of spatial relationships, enhancing grasp success under challenging occlusions. Furthermore, this representation facilitates active Next-Best-View (NBV) planning and optimizes sequential grasping strategies when direct grasping is infeasible. Additionally, we introduce a multi-view uncertainty-driven grasp fusion mechanism that refines grasp confidence and directional uncertainty in real-time, ensuring robust and stable grasp execution. Extensive real-world experiments demonstrate that VISO-Grasp achieves a success rate of 87.5% in target-oriented grasping with the fewest grasp attempts outperforming baselines. To the best of our knowledge, VISO-Grasp is the first unified framework integrating FMs into target-aware active view planning and 6-DoF grasping in environments with severe occlusions and entire invisibility constraints. Code is available at: https://github.com/YitianShi/vMF-Contact

Physical environments and circumstances are fundamentally dynamic, yet current 3D datasets and evaluation benchmarks tend to concentrate on either dynamic scenarios or dynamic situations in isolation, resulting in incomplete comprehension. To overcome these constraints, we introduce Situat3DChange, an extensive dataset supporting three situation-aware change understanding tasks following the perception-action model: 121K question-answer pairs, 36K change descriptions for perception tasks, and 17K rearrangement instructions for the action task. To construct this large-scale dataset, Situat3DChange leverages 11K human observations of environmental changes to establish shared mental models and shared situational awareness for human-AI collaboration. These observations, enriched with egocentric and allocentric perspectives as well as categorical and coordinate spatial relations, are integrated using an LLM to support understanding of situated changes. To address the challenge of comparing pairs of point clouds from the same scene with minor changes, we propose SCReasoner, an efficient 3D MLLM approach that enables effective point cloud comparison with minimal parameter overhead and no additional tokens required for the language decoder. Comprehensive evaluation on Situat3DChange tasks highlights both the progress and limitations of MLLMs in dynamic scene and situation understanding. Additional experiments on data scaling and cross-domain transfer demonstrate the task-agnostic effectiveness of using Situat3DChange as a training dataset for MLLMs. The established dataset and source code are publicly available at: https://github.com/RuipingL/Situat3DChange.

Action segmentation is a core challenge in high-level video understanding, aiming to partition untrimmed videos into segments and assign each a label from a predefined action set. Existing methods primarily address single-person activities with fixed action sequences, overlooking multi-person scenarios. In this work, we pioneer textual reference-guided human action segmentation in multi-person settings, where a textual description specifies the target person for segmentation. We introduce the first dataset for Referring Human Action Segmentation, i.e., RHAS133, built from 133 movies and annotated with 137 fine-grained actions with 33h video data, together with textual descriptions for this new task. Benchmarking existing action segmentation methods on RHAS133 using VLM-based feature extractors reveals limited performance and poor aggregation of visual cues for the target person. To address this, we propose a holistic-partial aware Fourier-conditioned diffusion framework, i.e., HopaDIFF, leveraging a novel cross-input gate attentional xLSTM to enhance holistic-partial long-range reasoning and a novel Fourier condition to introduce more fine-grained control to improve the action segmentation generation. HopaDIFF achieves state-of-the-art results on RHAS133 in diverse evaluation settings. The dataset and code are available at https://github.com/KPeng9510/HopaDIFF.

Understanding and decoding human brain activity from electroencephalography (EEG) signals is a fundamental problem in neuroscience and artificial intelligence, with applications ranging from cognition and emotion recognition to clinical diagnosis and brain–computer interfaces. While recent EEG foundation models have made progress in generalized brain decoding by leveraging unified architectures and large-scale pretraining, they inherit a scale-agnostic dense modeling paradigm from NLP and vision. This design overlooks an intrinsic property of neural activity—cross-scale spatiotemporal structure. Different EEG task patterns span a broad range of temporal and spatial scales, from brief neural activations to slow-varying rhythms, and from localized cortical activations to large-scale distributed interactions. Ignoring this diversity may lead to suboptimal representations and weakened generalization ability. To address these limitations, we propose CSBrain, a Cross-scale Spatiotemporal Brain foundation model for generalized EEG decoding. CSBrain introduces two key components: (i) Cross-scale Spatiotemporal Tokenization (CST), which aggregates multi-scale features within localized temporal windows and anatomical brain regions into compact scale-aware token representations; and (ii) Structured Sparse Attention (SSA), which models cross-window and cross-region dependencies for diverse decoding tasks, further enriching scale diversities while eliminating the spurious dependencies. CST and SSA are alternately stacked to progressively integrate cross-scale spatiotemporal dependencies. Extensive experiments across 11 representative EEG tasks and 16 datasets demonstrate that CSBrain consistently outperforms both task-specific models and strong foundation baselines. These results establish cross-scale modeling as a key inductive bias for generalized EEG decoding and highlight CSBrain as a robust backbone for future brain–AI research.

As an open research topic in the field of deep learning, learning with noisy labels has attracted much attention and grown rapidly over the past ten years. Learning with label noise is crucial for driver distraction behavior recognition, as real-world video data often contains mislabeled samples, impacting model reliability and performance. However, label noise learning is barely explored in the driver activity recognition field. In this paper, we propose the first label noise learning approach for the driver activity recognition task. Based on the cluster assumption, we initially enable the model to learn clustering-friendly low-dimensional representations from given videos and assign the resultant embeddings into clusters. We subsequently perform co-refinement within each cluster to smooth the classifier outputs. Furthermore, we propose a flexible sample selection strategy that combines two selection criteria without relying on any hyperparameters to filter clean samples from the training dataset. We also incorporate a self-adaptive parameter into the sample selection process to enforce balancing across classes. A comprehensive variety of experiments on the public Drive&Act dataset for all granularity levels demonstrates the superior performance of our method in comparison with other label-denoising methods derived from the image classification field. The source code is available at https://github.com/ilonafan/DAR-noisy-labels.

Industrial assembly requires rapid adaptation to complex procedures under constrained computing, connectivity, and privacy conditions, rendering cloud-based solutions impractical. We present an on-device assistant for real-time, semi-hands-free guidance, integrating lightweight detection, speech recognition, and retrieval-augmented response generation. To enable scalable training without manual labeling, we construct the Gear8 dataset via an automated pipeline and introduce a two-stage refinement strategy to enhance robustness against domain shift. Experiments show improved generalization under diverse corruptions. User studies confirm notable gains in efficiency and error reduction, underscoring the system’s suitability for real-world industrial deployment. The Gear8 dataset, models, and code are publicly available at: https://github.com/Kratos-Wen/Gear8.

In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones. However, using pure skeleton data in such open-set conditions poses challenges due to the lack of visual background cues and the distinct sparse structure of body pose sequences. In this paper, we tackle the unexplored Open-Set Skeleton-based Action Recognition (OS-SAR) task and formalize the benchmark on three skeleton-based datasets. We assess the performance of seven established open-set approaches on our task and identify their limits and critical generalization issues when dealing with skeleton information.To address these challenges, we propose a distance-based cross-modality ensemble method that leverages the cross-modal alignment of skeleton joints, bones, and velocities to achieve superior open-set recognition performance. We refer to the key idea as CrossMax - an approach that utilizes a novel cross-modality mean max discrepancy suppression mechanism to align latent spaces during training and a cross-modality distance-based logits refinement method during testing. CrossMax outperforms existing approaches and consistently yields state-of-the-art results across all datasets and backbones. We will release the benchmark, code, and models to the community.

Before developing a Document Layout Analysis (DLA) model in real-world applications, conducting comprehensive robustness testing is essential. However, the robustness of DLA models remains underexplored in the literature. To address this, we are the first to introduce a robustness benchmark for DLA models, which includes 450K document images of three datasets. To cover realistic corruptions, we propose a perturbation taxonomy with 12 common document perturbations with 3 severity levels inspired by realworld document processing. Additionally, to better understand document perturbation impacts, we propose two metrics, Mean Perturbation Effect (mPE) for perturbation assessment and Mean Robustness Degradation (mRD) for robustness evaluation. Furthermore, we introduce a self-titled model, i.e., Robust Document Layout Analyzer (RoDLA), which improves attention mechanisms to boost extraction of robust features. Experiments on the proposed benchmarks (PubLayNet-P, DocLayNet-P, andM6Doc-P) demonstrate that RoDLA obtains state-of-the-art mRD scores of 115.7, 135.4, and 150.4, respectively. Compared to previous methods, RoDLA achieves notable improvements in mAP of +3.8%, +7.1% and +12.1%, respectively.

Self-supervised representation learning for human action recognition has developed rapidly in recent years. Most of the existing works are based on skeleton data while using a multi-modality setup. These works overlooked the differences in performance among modalities, which led to the propagation of erroneous knowledge between modalities while only three fundamental modalities, i.e., joints, bones, and motions are used, hence no additional modalities are explored.In this work, we first propose an Implicit Knowledge Exchange Module (IKEM) which alleviates the propagation of erroneous knowledge between low-performance modalities. Then, we further propose three new modalities to enrich the complementary information between modalities. Finally, to maintain efficiency when introducing new modalities, we propose a novel teacher-student framework to distill the knowledge from the secondary modalities into the mandatory modalities considering the relationship constrained by anchors, positives, and negatives, named relational cross-modality knowledge distillation. The experimental results demonstrate the effectiveness of our approach, unlocking the efficient use of skeleton-based multi-modality data. Source code will be made publicly available at https://github.com/desehuileng0o0/IKEM.

The current state of machine learning scholarship in Timeseries Anomaly Detection (TAD) is plagued by the persistent use of flawed evaluation metrics, inconsistent benchmarking practices, and a lack of proper justification for the choices made in novel deep learning-based model designs. Our paper presents a critical analysis of the status quo in TAD, revealing the misleading track of current research and highlighting problematic methods, and evaluation practices. Our position advocates for a shift in focus from solely pursuing novel model designs to improving benchmarking practices, creating non-trivial datasets, and critically evaluating the utility of complex methods against simpler baselines. Our findings demonstrate the need for rigorous evaluation protocols, the creation of simple baselines, and the revelation that state-of-the-art deep anomaly detection models effectively learn linear mappings. These findings suggest the need for more exploration and development of simple and interpretable TAD methods. The increment of model complexity in the state-of-the-art deep-learning based models unfortunately offers very little improvement. We offer insights and suggestions for the field to move forward.

Synthetic data generation is a proven method for augmenting training sets without the need for extensive setups, yet its application in human activity recognition is underexplored. This is particularly crucial for human-robot collaboration in household settings, where data collection is often privacy-sensitive. In this paper, we introduce SynthAct, a synthetic data generation pipeline designed to significantly minimize the reliance on real-world data. Leveraging modern 3D pose estimation techniques, SynthAct can be applied to arbitrary 2D or 3D video action recordings, making it applicable for uncontrolled in-the-field recordings by robotic agents or smarthome monitoring systems. We present two SynthAct datasets: AMARV, a large synthetic collection with over 800k multi-view action clips, and Synthetic Smarthome, mirroring the Toyota Smarthome dataset. SynthAct generates a rich set of data, including RGB videos and depth maps from four synchronized views, 3D body poses, normal maps, segmentation masks and bounding boxes. We validate the efficacy of our datasets through extensive synthetic-to-real experiments on NTU RGB+D and Toyota Smarthome. SynthAct is available on our project page4.

People with Visual Impairments (PVI) typically recognize objects through haptic perception. Knowing objects and materials before touching is desired by the target users but under-explored in the field of human-centered robotics. To fill this gap, in this work, a wearable vision-based robotic system, MATERobot, is established for PVI to recognize materials and object categories beforehand. To address the computational constraints of mobile platforms, we propose a lightweight yet accurate model MATEViT to perform pixel-wise semantic segmentation, simultaneously recognizing both objects and materials. Our methods achieve respective 40.2% and 51.1% of mIoU on COCOStuff-10K and DMS datasets, surpassing the previous method with +5.7% and +7.0% gains. Moreover, on the field test with participants, our wearable system reaches a score of 28 in the NASA-Task Load Index, indicating low cognitive demands and ease of use. Our MATERobot demonstrates the feasibility of recognizing material property through visual cues and offers a promising step towards improving the functionality of wearable robots for PVI. The source code has been made publicly available at MATERobot.

Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of activity sequences is time-consuming and the resulting labels are often noisy. If not effectively addressed, label noise negatively affects the model’s training, resulting in lower recognition quality. Despite its importance, addressing label noise for skeleton-based action recognition has been overlooked so far. In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark. Observations reveal that these baselines yield only marginal performance when dealing with sparse skeleton data. Consequently, we introduce a novel methodology, NoiseEraSAR, which integrates global sample selection, co-teaching, and Cross-Modal Mixture-of-Experts (CM-MOE) strategies, aimed at mitigating the adverse impacts of label noise. Our proposed approach demonstrates better performance on the established benchmark, setting new state-of-the-art standards. The source code for this study will be made accessible at https://github.com/xuyizdby/NoiseEraSAR.

Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework. However, the modality incompleteness in multi-modal segmentation remains under-explored. In this work, we establish a task called Modality-Incomplete Scene Segmentation (MISS), which encompasses both system-level modality absence and sensor-level modality errors. To avoid the predominant modality reliance in multi-modal fusion, we introduce a Missing-aware Modal Switch (MMS) strategy to proactively manage missing modalities during training. Utilizing bit-level batch-wise sampling enhances the model’s performance in both complete and incomplete testing scenarios. Furthermore, we introduce the Fourier Prompt Tuning (FPT) method to incorporate representative spectral information into a limited number of learnable prompts that maintain robustness against all MISS scenarios. Akin to fine-tuning effects but with fewer tunable parameters (1.1%). Extensive experiments prove the efficacy of our proposed approach, showcasing an improvement of 5.84% mIoU over the prior state-of-the-art parameter-efficient methods in modality missing. The source code is publicly available at https://github.com/RuipingL/MISS.

In this paper, we tackle the new task of video-based Activated Muscle Group Estimation (AMGE) aiming at identifying active muscle regions during physical activity in the wild.To this intent, we provide the MuscleMap dataset featuring >15𝐾 video clips with 135 different activities and 20 labeled muscle groups.This dataset opens the vistas to multiple video-based applications in sports and rehabilitation medicine under flexible environment constraints.The proposed MuscleMap dataset is constructed with YouTube videos, specifically targeting High-Intensity Interval Training (HIIT) physical exercise in the wild.To make the AMGE model applicable in real-life situations, it is crucial to ensure that the model can generalize well to numerous types of physical activities not present during training and involving new combinations of activated muscles.To achieve this, our benchmark also covers an evaluation setting where the model is exposed to activity types excluded from the training set.Our experiments reveal that the generalizability of existing architectures adapted for the AMGE task remains a challenge.Therefore, we also propose a new approach, TransM 3 E, which employs a multi-modality feature fusion mechanism between both the video transformer model and the skeleton-based graph convolution model with novel cross-modal knowledge distillation executed on multiclassification tokens.The proposed method surpasses all popular video classification models when dealing with both, previously seen and new types of physical activities.The database and code can be found at https://github.com/KPeng9510/MuscleMap.

In Open-Set Domain Generalization (OSDG), the model is exposed to both new variations of data appearance (domains) and open-set conditions, where both known and novel categories are present at test time. The challenges of this task arise from the dual need to generalize across diverse domains and accurately quantify category novelty, which is critical for applications in dynamic environments. Recently, meta-learning techniques have demonstrated superior results in OSDG, effectively orchestrating the meta-train and -test tasks by employing varied random categories and predefined domain partition strategies. These approaches prioritize a well-designed training schedule over traditional methods that focus primarily on data augmentation and the enhancement of discriminative feature learning. The prevailing meta-learning models in OSDG typically utilize a predefined sequential domain scheduler to structure data partitions. However, a crucial aspect that remains inadequately explored is the influence brought by strategies of domain schedulers during training. In this paper, we observe that an adaptive domain scheduler benefits more in OSDG compared with prefixed sequential and random domain schedulers. We propose the Evidential Bi-Level Hardest Domain Scheduler (EBiL-HaDS) to achieve an adaptive domain scheduler. This method strategically sequences domains by assessing their reliabilities in utilizing a follower network, trained with confidence scores learned in an evidential manner, regularized by max rebiasing discrepancy, and optimized in a bilevel manner. We verify our approach on three OSDG benchmarks, i.e., PACS, DigitsDG, and OfficeHome. The results show that our method substantially improves OSDG performance and achieves more discriminative embeddings for both the seen and unseen categories, underscoring the advantage of a judicious domain scheduler for the generalizability to unseen domains and unseen categories. The source code is publicly available at https://github.com/KPeng9510/EBiL-HaDS.

Exploring the intricate dynamics between muscular and skeletal structures is pivotal for understanding human motion. This domain presents substantial challenges, primarily attributed to the intensive resources required for acquiring ground truth muscle activation data, resulting in a scarcity of datasets.In this work, we address this issue by establishing Muscles in Time (MinT), a large-scale synthetic muscle activation dataset.For the creation of MinT, we enriched existing motion capture datasets by incorporating muscle activation simulations derived from biomechanical human body models using the OpenSim platform, a common framework used in biomechanics and human motion research.Starting from simple pose sequences, our pipeline enables us to extract detailed information about the timing of muscle activations within the human musculoskeletal system.Muscles in Time contains over nine hours of simulation data covering 227 subjects and 402 simulated muscle strands. We demonstrate the utility of this dataset by presenting results on neural network-based muscle activation estimation from human pose sequences with two different sequence-to-sequence architectures.

Seeing only a tiny part of the whole is not knowing the full circumstance. Bird’s-eye-view (BEV) perception, a process of obtaining allocentric maps from egocentric views, is restricted when using a narrow Field of View (FoV) alone. In this work, mapping from 360° panoramas to BEV semantics, the 360BEV task, is established for the first time to achieve holistic representations of indoor scenes in a top-down view. Instead of relying on narrow-FoV image sequences, a panoramic image with depth information is sufficient to generate a holistic BEV semantic map. To benchmark 360BEV, we present two indoor datasets, 360BEV-Matterport and 360BEV-Stanford, both of which include egocentric panoramic images and semantic segmentation labels, as well as allocentric semantic maps. Besides delving deep into different mapping paradigms, we propose a dedicated solution for panoramic semantic mapping, namely 360Mapper. Through extensive experiments, our methods achieve 44.32% and 45.78% mIoU on both datasets respectively, surpassing previous counterparts with gains of +7.60% and +9.70% in mIoU.1

In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the$360^\circ$imagery. To tackle these problems, first, we propose the upgraded Transformer for Panoramic Semantic Segmentation, ie, Trans4PASS+, equipped withDeformable Patch Embedding (DPE)andDeformable MLP (DMLPv2)modules for handling object deformations and image distortions whenever (before or after adaptation) and wherever (shallow or deep levels). Second, we enhance theMutual Prototypical Adaptation (MPA)strategy via pseudo-label rectification for unsupervised domain adaptive panoramic segmentation. Third, aside from Pinhole-to-Panoramic (Pin2Pan) adaptation, we create a new dataset (SynPASS) with 9,080 panoramic images, facilitating Synthetic-to-Real (Syn2Real) adaptation scheme in$360^\circ$imagery. Extensive experiments are conducted, which cover indoor and outdoor scenarios, and each of them is investigated withPin2PanandSyn2Realregimens. Trans4PASS+ achieves state-of-the-art performances on four domain adaptive panoramic semantic segmentation benchmarks. Code is available athttps://github.com/jamycheung/Trans4PASS.

This paper introduces the task of Auditory Referring Multi-Object Tracking (AR-MOT), which dynamically tracks specific objects in a video sequence based on audio expressions and appears as a challenging problem in autonomous driving. Due to the lack of semantic modeling capacity in audio and video, existing works have mainly focused on text-based multi-object tracking, which often comes at the cost of tracking quality, interaction efficiency, and even the safety of assistance systems, limiting the application of such methods in autonomous driving. In this paper, we delve into the problem of AR-MOT from the perspective of audio-video fusion and audio-video tracking. We put forward EchoTrack, an end-to-end AR-MOT framework with dual-stream vision transformers. The dual streams are intertwined with our Bidirectional Frequency-domain Cross-attention Fusion Module (Bi-FCFM), which bidirectionally fuses audio and video features from both frequency- and spatiotemporal domains. Moreover, we propose the Audio-visual Contrastive Tracking Learning (ACTL) regime to extract homogeneous semantic features between expressions and visual objects by learning homogeneous features between different audio and video objects effectively. Aside from the architectural design, we establish the first set of large-scale AR-MOT benchmarks, including Echo-KITTI, Echo-KITTI+, and Echo-BDD. Extensive experiments on the established benchmarks demonstrate the effectiveness of the proposed EchoTrack and its components. The source code and datasets are available athttps://github.com/lab206/EchoTrack.

Semantic segmentation benchmarks in the realm of autonomous driving are dominated by large pre-trained transformers, yet their widespread adoption is impeded by substantial computational costs and prolonged training durations. To lift this constraint, we look at efficient semantic segmentation from a perspective of comprehensive knowledge distillation and aim to bridge the gap between multi-source knowledge extractions and transformer-specific patch embeddings. We put forward the Transformer-based Knowledge Distillation (TransKD) framework which learns compact student transformers by distilling both feature maps and patch embeddings of large teacher transformers, bypassing the long pre-training process and reducing the FLOPs by >85.0%. Specifically, we propose two fundamental modules to realize feature map distillation and patch embedding distillation, respectively: 1) Cross Selective Fusion (CSF) enables knowledge transfer between cross-stage features via channel attention and feature map distillation within hierarchical transformers; 2) Patch Embedding Alignment (PEA) performs dimensional transformation within the patchifying process to facilitate the patch embedding distillation. Furthermore, we introduce two optimization modules to enhance the patch embedding distillation from different perspectives: 1) Global-Local Context Mixer (GL-Mixer) extracts both global and local information of a representative embedding; 2) Embedding Assistant (EA) acts as an embedding method to seamlessly bridge teacher and student models with the teacher’s number of channels. Experiments on Cityscapes, ACDC, NYUv2, and Pascal VOC2012 datasets show that TransKD outperforms state-of-the-art distillation frameworks and rivals the time-consuming pre-training method. The source code is publicly available athttps://github.com/RuipingL/TransKD.

Multimodal fusion can make semantic segmentation more robust. However, fusing an arbitrary number of modalities remains underexplored. To delve into this problem, we create the Deliver arbitrary-modal segmentation benchmark, covering Depth, LiDAR, multiple Views, Events, and RGB. Aside from this, we provide this dataset in four severe weather conditions as well as five sensor failure cases to exploit modal complementarity and resolve partial outages. To make this possible, we present the arbitrary cross-modal segmentation model CMNEXT. It encompasses a Self-Query Hub (SQ-Hub) designed to extract effective information from any modality for subsequent fusion with the RGB representation and adds only negligible amounts of parameters ~0.1M) per additional modality. On top, to efficiently and flexibly harvest discriminative cues from the auxiliary modalities, we introduce the simple Parallel Pooling Mixer (PPX). With extensive experiments on a total of six benchmarks, our CMNEXT achieves state-of-the-art performance on the Deliver, Kitti-360, MFNet, NYU Depth V2, UrbanLF, and MCubeS datasets, allowing to scale from 1 to 81 modalities. On the freshly collected Deliver, the quad-modal CMNEXT reaches up to 66.30% in mIoU with a +9.10% gain as compared to the mono-modal baseline.11The Deliver dataset and our code will be made publicly available at https://jamycheung.github.io/DELIVER.html.

Deep learning-based models are at the top of most driver observation benchmarks due to their remarkable accuracies but come with a high computational cost, while the resources are often limited in real-world driving scenarios. This paper presents a lightweight framework for resource- efficient driver activity recognition. We enhance 3D MobileNet, a speed-optimized neural architecture for video classification, with two paradigms for improving the trade-off between model accuracy and computational efficiency: knowledge distillation and model quantization. Knowledge distillation prevents large drops in accuracy when reducing the model size by harvesting knowledge from a large teacher model (I3D) via soft labels instead of using the original ground truth. Quantization further drastically reduces the memory and computation requirements by representing the model weights and activations using lower precision integers. Extensive experiments on a public dataset for in-vehicle monitoring during autonomous driving show that our proposed framework leads to an 3- fold reduction in model size and 1.4-fold improvement in inference time compared to an already speed-optimized architecture. Our code is available at https://github.com/calvintanama/qd-driver-activity-reco.

Humans have an innate ability to sense their surroundings, as they can extract the spatial representation from the egocentric perception and form an allocentric semantic map via spatial transformation and memory updating. However, endowing mobile agents with such a spatial sensing ability is still a challenge, due to two difficulties: (1) the previous convolutional models are limited by the local receptive field, thus, struggling to capture holistic long-range dependencies during observation; (2) the excessive computational budgets required for success, often lead to a separation of the mapping pipeline into stages, resulting the en-tire mapping process inefficient. To address these issues, we propose an end-to-end one-stage Transformer-based frame-work for Mapping, termed Trans4Map. Our egocentric-to-allocentric mapping process includes three steps: (1) the efficient transformer extracts the contextual features from a batch of egocentric images; (2) the proposed Bidirectional Allocentric Memory (BAM) module projects egocentric features into the allocentric memory; (3) the map de-coder parses the accumulated memory and predicts the top-down semantic segmentation map. In contrast, Trans4Map achieves state-of-the-art results, reducing 67.2% parameters, yet gaining a +3.25% mIoU and a +4.09% mBF1 improvements on the Matterport3D dataset.1

Occlusions areuniversal disruptions constantly present in the real world. Especially for sparse representations, such as human skeletons, a few occluded points might destroy the geometrical and temporal continuity critically affecting the results. Yet, the research of data-scarce recognition from skeleton sequences, such as one-shot action recognition, does not explicitly consider occlusions despite their everyday pervasiveness. In this work, we explicitly tackle body occlusions forSkeleton-basedOne-shotActionRecognition (SOAR). We mainly consider two occlusion variants: 1) random occlusions and 2) more realistic occlusions caused by diverse everyday objects, which we generate by projecting the existing IKEA 3D furniture models into the camera coordinate system of the 3D skeletons with different geometric parameters, (e.g., rotation and displacement). We leverage the proposed pipeline to blend out portions of skeleton sequences of the three popular action recognition datasets (NTU-120, NTU-60 and Toyota Smart Home) and formalize the first benchmark for SOAR from partially occluded body poses. This is the first benchmark which considers occlusions for data-scarce action recognition. Another key property of our benchmark are the more realistic occlusions generated by everyday objects, as even in standard recognition from 3D skeletons, only randomly missing joints were considered. We re-evaluate existing state-of-the-art frameworks for SOAR in the light of this new task and further introduceTrans4SOAR– a new transformer-based model which leverages three data streams and mixed attention fusion mechanism to alleviate the adverse effects caused by occlusions. While our experiments demonstrate a clear decline in accuracy with missing skeleton portions, this effect is smaller withTrans4SOAR, which outperforms other architectures on all datasets. Although we specifically focus onocclusions,Trans4SOARadditionally yields state-of-the-art in thestandardSOAR without occlusion, surpassing the best published approach by 2.85% on NTU-120.

Panoramic images with their 360° directional view encompass exhaustive information about the surrounding space, providing a rich foundation for scene understanding. To unfold this potential in the form of robust panoramic segmentation models, large quantities of expensive, pixel-wise annotations are crucial for success. Such annotations are available, but predominantly for narrow-angle, pinhole-camera images which, off the shelf, serve as sub-optimal resources for training panoramic models. Distortions and the distinct image-feature distribution in 360° panoramas impede the transfer from the annotation-rich pinhole domain and therefore come with a big dent in performance. To get around this domain difference and bring together semantic annotations from pinhole- and 360° surround-visuals, we propose to learn object deformations and panoramic image distortions in the Deformable Patch Embedding (DPE) and Deformable MLP (DMLP) components which blend into our Transformer for PAnoramic Semantic Segmentation (Trans4PASS) model. Finally, we tie together shared semantics in pinhole- and panoramic feature embeddings by generating multi-scale prototype features and aligning them in our Mutual Prototypical Adaptation (MPA) for unsupervised domain adaptation. On the indoor Stanford2D3D dataset, our Trans4PASS with MPA maintains comparable performance to fully-supervised state-of-the-arts, cutting the need for over 1,400 labeled panoramas. On the outdoor DensePASS dataset, we break state-of-the-art by 14.39% mIoU and set the new bar at 56.38%.

Traditional video-based human activity recognition has experienced remarkable progress linked to the rise of deep learning, but this effect was slower as it comes to the downstream task of driver behavior understanding. Understanding the situation inside the vehicle cabin is essential for Advanced Driving Assistant System (ADAS) as it enables identifying distraction, predicting driver's intent and leads to more convenient human-vehicle interaction. At the same time, driver observation systems face substantial obstacles as they need to capture different granularities of driver states, while the complexity of such secondary activities grows with the rising automation and increased driver freedom. Furthermore, a model is rarely deployed under conditions identical to the ones in the training set, as sensor placements and types vary from vehicle to vehicle, constituting a substantial obstacle for real-life deployment of data-driven models. In this work, we present a novel vision-based framework for recognizing secondary driver behaviours based on visual transformers and an additional augmented feature distribution calibration module. This module operates in the latent feature-space enriching and diversifying the training set at feature-level in order to improve generalization to novel data appearances, (e.g., sensor changes) and general feature quality. Our framework consistently leads to better recognition rates, surpassing previous state-of-the-art results of the public Drive&Act benchmark on all granularity levels. Our code will be made publicly available at https://github.com/KPeng9510/TransDARC.

Visual recognition inside the vehicle cabin leads to safer driving and more intuitive human-vehicle interaction but such systems face substantial obstacles as they need to capture different granularities of driver behaviour while dealing with highly limited body visibility and changing illumination. Multimodal recognition mitigates a number of such issues: prediction outcomes of different sensors complement each other due to different modality-specific strengths and weaknesses. While several late fusion methods have been considered in previously published frameworks, they constantly feature different architecture backbones and building blocks making it very hard to isolate the role of the chosen late fusion strategy itself.This paper presents an empirical evaluation of different paradigms for decision-level late fusion in video-based driver observation. We compare seven different mechanisms for joining the results of single-modal classifiers which have been both popular, (e.g. score averaging) and not yet considered (e.g. rank-level fusion) in the context of driver observation evaluating them based on different criteria and benchmark settings. This is the first systematic study of strategies for fusing outcomes of multimodal predictors inside the vehicles, conducted with the goal to provide guidance for fusion scheme selection.

Autonomous vehicles clearly benefit from the expanded Field of View (FoV) of 360° sensors, but modern semantic segmentation approaches rely heavily on annotated training data which is rarely available forpanoramicimages. We look at this problem from the perspective of domain adaptation and bringpanoramicsemantic segmentation to a setting, where labelled training data originates from a different distribution of conventionalpinholecamera images. To achieve this, we formalize the task of unsupervised domain adaptation for panoramic semantic segmentation and collect DensePass - a novel densely annotated dataset for panoramic segmentation under cross-domain conditions, specifically built to study the Pinhole$\rightarrow$PANORAMIC domain shift and accompanied with pinhole camera training examples obtained from Cityscapes. DensePass covers both, labelled- and unlabelled 360° images, with the labelled data comprising 19 classes which explicitly fit the categories available in the source (i.e.pinhole) domain. Since data-driven models are especially susceptible to changes in data distribution, we introduce P2PDA - a generic framework for Pinhole$\rightarrow$Panoramic semantic segmentation which addresses the challenge of domain divergence with different variants of attention-augmented domain adaptation modules, enabling the transfer in output-, feature-, and feature confidence spaces. P2PDA intertwines uncertainty-aware adaptation using confidence values regulated on-the-fly through attention heads with discrepant predictions. Our framework facilitates context exchange when learning domain correspondences and dramatically improves the adaptation performance of accuracy- and efficiency-focused models. Comprehensive experiments verify that our framework clearly surpasses unsupervised domain adaptation- and specialized panoramic segmentation approaches as well as state-of-the-art semantic segmentation methods.

At the heart of all automated driving systems is the ability to sense the surroundings,e.g.,through semantic segmentation of LiDAR sequences, which experienced a remarkable progress due to the release of large datasets such as SemanticKITTI and nuScenes-LidarSeg. While most previous works focus onsparsesegmentation of the LiDAR input,denseoutput masks provide self-driving cars with almost complete environment information. In this paper, we introduce MASS - a Multi-Attentional Semantic Segmentation model specifically built for dense top-view understanding of the driving scenes. Our framework operates on pillar- and occupancy features and comprises three attention-based building blocks: (1) a keypoint-driven graph attention, (2) an LSTM-based attention computed from a vector embedding of the spatial input, and (3) a pillar-based attention, resulting in a dense 360° segmentation mask. With extensive experiments on both, SemanticKITTI and nuScenes-LidarSeg, we quantitatively demonstrate the effectiveness of our model, outperforming the state of the art by 19.0% on SemanticKITTI and reaching 30.4% in mIoU on nuScenes-LidarSeg, where MASS is the first work addressing the dense segmentation task. Furthermore, our multi-attention model is shown to be very effective for 3D object detection validated on the KITTI-3D dataset, showcasing its high generalizability to other tasks related to 3D vision.

Driver observation models are rarely deployed under perfect conditions. In practice, illumination, camera placement and type differ from the ones present during training and unforeseen behaviours may occur at any time. While observing the human behind the steering wheel leads to more intuitive human-vehicle-interaction and safer driving, it requires recognition algorithms which do not only predict the correct driver state, but also determine their prediction quality through realistic and interpretable confidence measures. Reliable uncertainty estimates are crucial for building trust and are a serious obstacle for deploying activity recognition networks in real driving systems. In this work, we for the first time examine how well the confidence values of modern driver observation models indeed match the probability of the correct outcome and show that raw neural network-based approaches tend to significantly overestimate their prediction quality. To correct this misalignment between the confidence values and the actual uncertainty, we consider two strategies. First, we enhance two activity recognition models often used for driver observation with temperature scaling – an off-the-shelf method for confidence calibration in image classification. Then, we introduce Calibrated Action Recognition with Input Guidance (CARING) – a novel approach leveraging an additional neural network to learn scaling the confidences depending on the video representation. Extensive experiments on the Drive&Act dataset demonstrate that both strategies drastically improve the quality of model confidences, while our CARING model outperforms both, the original architectures and their temperature scaling enhancement, leading to best uncertainty estimates.

Transparent objects, such as glass walls and doors, constitute architectural obstacles hindering the mobility of people with low vision or blindness. For instance, the open space behind glass doors is inaccessible, unless it is correctly perceived and interacted with. However, traditional assistive technologies rarely cover the segmentation of these safety-critical transparent objects. In this paper, we build a wearable system with a novel dual-head Transformer for Transparency (Trans4Trans) perception model, which can segment general- and transparent objects. The two dense segmentation results are further combined with depth information in the system to help users navigate safely and assist them to negotiate transparent obstacles. We propose a lightweight Transformer Parsing Module (TPM) to perform multi-scale feature interpretation in the transformer-based decoder. Benefiting from TPM, the double decoders can perform joint learning from corresponding datasets to pursue robustness, meanwhile maintain efficiency on a portable GPU, with negligible calculation increase. The entire Trans4Trans model is constructed in a symmetrical encoder-decoder architecture, which outperforms state-of-the-art methods on the test sets of Stanford2D3D and Trans10K-v2 datasets, obtaining mIoU of 45.13% and 75.14%, respectively. Through a user study and various pre-tests conducted in indoor and outdoor scenes, the usability and reliability of our assistive system have been extensively verified. Meanwhile, the Tran4Trans model has outstanding performances on driving scene datasets. On Cityscapes, ACDC, and DADA-seg datasets corresponding to common environments, adverse weather, and traffic accident scenarios, mIoU scores of 81.5%, 76.3%, and 39.2% are obtained, demonstrating its high efficiency and robustness for real-world transportation applications.

Human affect recognition is a well-established research area with numerous applications, e.g. in psychological care, but existing methods assume that all emotions-of-interest are given a priori as annotated training examples. However, the rising granularity and refinements of the human emotional spectrum through novel psychological theories and the increased consideration of emotions in context brings considerable pressure to data collection and labeling work. In this paper, we conceptualize one-shot recognition of emotions in context - a new problem aimed at recognizing human affect states in finer particle level from a single support sample. To address this challenging task, we follow the deep metric learning paradigm and introduce a multi-modal emotion embedding approach which minimizes the distance of the same-emotion embeddings by leveraging complementary information of human appearance and the semantic scene context obtained through a semantic segmentation network. All streams of our context-aware model are optimized jointly using weighted triplet loss and weighted cross entropy loss. We conduct thorough experiments on both, categorical and numerical emotion recognition tasks of the Emotic dataset adapted to our one-shot recognition problem, revealing that categorizing human affect from a single example is a hard task. Still, all variants of our model clearly outperform the random baseline, while leveraging the semantic scene context consistently improves the learnt representations, setting state-of-the-art results in one-shot emotion recognition. To foster research of more universal representations of human affect states, we will make our benchmark and models publicly available to the community under https://github.com/KPeng9510/Affect-DML.

Semantic understanding of the surrounding environment is essential for automated vehicles. The recent publication of the SemanticKITTI dataset stimulates the research on semantic segmentation of LiDAR point clouds in urban scenarios. While most existing approaches predict sparse pointwise semantic classes for the sparse input LiDAR scan, we propose PillarSegNet to be able to output a dense semantic grid map. In contrast to a previously proposed grid map method, PillarSegNet uses PointNet to learn features directly from the 3D point cloud and then conducts 2D semantic segmentation in the top view. To train and evaluate our approach, we use both sparse and dense ground truth, where the dense ground truth is obtained from multiple superimposed scans. Experimental results on the SemanticKITTI dataset show that PillarSegNet achieves a performance gain of about 10% mIoU over the state-of-the-art grid map method.