John See

Huabin Liu, Weixian Lv, John See et al.

A primary challenge faced in few-shot action recognition is inadequate video data for training. To address this issue, current methods in this field mainly focus on devising algorithms at the feature level while little attention is paid to processing input video data. Moreover, existing frame sampling strategies may omit critical action information in temporal and spatial dimensions, which further impacts video utilization efficiency. In this paper, we propose a novel video frame sampler for few-shot action recognition to address this issue, where task-specific spatial-temporal frame sampling is achieved via a temporal selector (TS) and a spatial amplifier (SA). Specifically, our sampler first scans the whole video at a small computational cost to obtain a global perception of video frames. The TS plays its role in selecting top-T frames that contribute most significantly and subsequently. The SA emphasizes the discriminative information of each frame by amplifying critical regions with the guidance of saliency maps. We further adopt task-adaptive learning to dynamically adjust the sampling strategy according to the episode task at hand. Both the implementations of TS and SA are differentiable for end-to-end optimization, facilitating seamless integration of our proposed sampler with most few-shot action recognition methods. Extensive experiments show a significant boost in the performances on various benchmarks including long-term videos.The code is available at https://github.com/R00Kie-Liu/Sampler

Tao Wang, Kean Chen, Weiyao Lin et al.

Multiple Object Tracking (MOT) focuses on modeling the relationship of detected objects among consecutive frames and merge them into different trajectories. MOT remains a challenging task as noisy and confusing detection results often hinder the final performance. Furthermore, most existing research are focusing on improving detection algorithms and association strategies. As such, we propose a novel framework that can effectively predict and mask-out the noisy and confusing detection results before associating the objects into trajectories. In particular, we formulate such "bad" detection results as a sequence of events and adopt the spatio-temporal point process}to model such events. Traditionally, the occurrence rate in a point process is characterized by an explicitly defined intensity function, which depends on the prior knowledge of some specific tasks. Thus, designing a proper model is expensive and time-consuming, with also limited ability to generalize well. To tackle this problem, we adopt the convolutional recurrent neural network (conv-RNN) to instantiate the point process, where its intensity function is automatically modeled by the training data. Furthermore, we show that our method captures both temporal and spatial evolution, which is essential in modeling events for MOT. Experimental results demonstrate notable improvements in addressing noisy and confusing detection results in MOT datasets. An improved state-of-the-art performance is achieved by incorporating our baseline MOT algorithm with the spatio-temporal point process model.

Xue Qin, Simin Luan, John See et al.

Canary deployment routes a fraction of traffic to a new software version, monitors metrics, and rolls back on regression. Mainstream controllers (Argo Rollouts, Spinnaker, Flagger) change the deployed system's cryptographic identity during the canary window. The drift is harmless for stateless microservices but breaks the claim that "the agent you certified is still the agent you have" for safety-critical embodied agents, forcing re-certification per canary. We present ICAN-Deploy (Identity-stable CANary Deployment), a middleware construction whose state machine holds the identity hash invariant across the canary window by separating capability names (frozen, hashed) from capability versions (mutable runtime state). We implement ICAN-Deploy inside a runtime governance layer for LLM-driven robots and verify invariance by closed-form proof, AST lint, and TLA+ model-checking, then corroborate over N=100 real canary cycles on a Franka Panda arm in MuJoCo (zero drift; entry latency 95% BCa CI [1.52, 2.01] ms). A feature-flagged strawman that folds versions into the manifest falsifies on the same workload. A system certified once at identity-creation time can then ship arbitrary capability evolution under that same certification, within the version-and-name envelope.

Cong Yang, Bipin Indurkhya, John See et al.

Skeleton Ground Truth (GT) is critical to the success of supervised skeleton extraction methods, especially with the popularity of deep learning techniques. Furthermore, we see skeleton GTs used not only for training skeleton detectors with Convolutional Neural Networks (CNN) but also for evaluating skeleton-related pruning and matching algorithms. However, most existing shape and image datasets suffer from the lack of skeleton GT and inconsistency of GT standards. As a result, it is difficult to evaluate and reproduce CNN-based skeleton detectors and algorithms on a fair basis. In this paper, we present a heuristic strategy for object skeleton GT extraction in binary shapes and natural images. Our strategy is built on an extended theory of diagnosticity hypothesis, which enables encoding human-in-the-loop GT extraction based on clues from the target's context, simplicity, and completeness. Using this strategy, we developed a tool, SkeView, to generate skeleton GT of 17 existing shape and image datasets. The GTs are then structurally evaluated with representative methods to build viable baselines for fair comparisons. Experiments demonstrate that GTs generated by our strategy yield promising quality with respect to standard consistency, and also provide a balance between simplicity and completeness.

Xianbao Hou, Yonghao He, Zeyd Boukhers et al.

Diffusion models have significantly mitigated the impact of annotated data scarcity in remote sensing (RS). Although recent approaches have successfully harnessed these models to enable diverse and controllable Layout-to-Image (L2I) synthesis, they still suffer from limited fine-grained control and fail to strictly adhere to bounding box constraints. To address these limitations, we propose RSGen, a plug-and-play framework that leverages diverse edge guidance to enhance layout-driven RS image generation. Specifically, RSGen employs a progressive enhancement strategy: 1) it first enriches the diversity of edge maps composited from retrieved training instances via Image-to-Image generation; and 2) subsequently utilizes these diverse edge maps as conditioning for existing L2I models to enforce pixel-level control within bounding boxes, ensuring the generated instances strictly adhere to the layout. Extensive experiments across three baseline models demonstrate that RSGen significantly boosts the capabilities of existing L2I models. For instance, with CC-Diff on the DOTA dataset for oriented object detection, we achieve remarkable gains of +9.8/+12.0 in YOLOScore mAP50/mAP50-95 and +1.6 in mAP on the downstream detection task. Our code will be publicly available: https://github.com/D-Robotics-AI-Lab/RSGen

Yiquan Gao, John See

By contrast with the prevailing works of low-light enhancement in natural images and videos, this study copes with the low-illumination quality degradation in anime scenery images to bridge the domain gap. For such an underexplored enhancement task, we first curate images from various sources and construct an unpaired anime scenery dataset with diverse environments and illumination conditions to address the data scarcity. To exploit the power of uncertainty information inherent with the diverse illumination conditions, we propose a Data Relativistic Uncertainty (DRU) framework, motivated by the idea from Relativistic GAN. By analogy with the wave-particle duality of light, our framework interpretably defines and quantifies the illumination uncertainty of dark/bright samples, which is leveraged to dynamically adjust the objective functions to recalibrate the model learning under data uncertainty. Extensive experiments demonstrate the effectiveness of DRU framework by training several versions of EnlightenGANs, yielding superior perceptual and aesthetic qualities beyond the state-of-the-art methods that are incapable of learning from data uncertainty perspective. We hope our framework can expose a novel paradigm of data-centric learning for potential visual and language domains. Code is available.

Xue Qin, Simin Luan, John See et al.

Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through prompt engineering, policy updates, or structural redesign -- leading to instability and loss of identity in long-lived systems. In this work, we propose a capability-centric evolution paradigm for embodied agents. We argue that a robot should maintain a persistent agent as its cognitive identity, while enabling continuous improvement through the evolution of its capabilities. Specifically, we introduce the concept of Embodied Capability Modules (ECMs), which represent modular, versioned units of embodied functionality that can be learned, refined, and composed over time. We present a unified framework in which capability evolution is decoupled from agent identity. Capabilities evolve through a closed-loop process involving task execution, experience collection, model refinement, and module updating, while all executions are governed by a runtime layer that enforces safety and policy constraints. We demonstrate through simulated embodied tasks that capability evolution improves task success rates from 32.4% to 91.3% over 20 iterations, outperforming both agent-modification baselines and established skill-learning methods (SPiRL, SkiMo), while preserving zero policy drift and zero safety violations. Our results suggest that separating agent identity from capability evolution provides a scalable and safe foundation for long-term embodied intelligence.

Xue Qin, Simin Luan, John See et al.

Embodied agents are increasingly expected to improve over time by updating their executable capabilities rather than rewriting the agent itself. Prior work has separately studied modular capability packaging, capability evolution, and runtime governance. However, a key systems problem remains underexplored: once an embodied capability module evolves into a new version, how can the hosting system deploy it safely without breaking policy constraints, execution assumptions, or recovery guarantees? We formulate governed capability evolution as a first-class systems problem for embodied agents. We propose a lifecycle-aware upgrade framework in which every new capability version is treated as a governed deployment candidate rather than an immediately executable replacement. The framework introduces four upgrade compatibility checks -- interface, policy, behavioral, and recovery -- and organizes them into a staged runtime pipeline comprising candidate validation, sandbox evaluation, shadow deployment, gated activation, online monitoring, and rollback. We evaluate over 6 rounds of capability upgrade with 15 random seeds. Naive upgrade achieves 72.9% task success but drives unsafe activation to 60% by the final round; governed upgrade retains comparable success (67.4%) while maintaining zero unsafe activations across all rounds (Wilcoxon p=0.003). Shadow deployment reveals 40% of regressions invisible to sandbox evaluation alone, and rollback succeeds in 79.8% of post-activation drift scenarios.

Xue Qin, Simin Luan, John See et al.

Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once granted execution authority, the central challenge becomes how to keep actions governable at runtime. Existing approaches embed safety and recovery logic inside the agent loop, making execution control difficult to standardize, audit, and adapt. This paper argues that embodied intelligence requires not only stronger agents, but stronger runtime governance. We propose a framework for policy-constrained execution that separates agent cognition from execution oversight. Governance is externalized into a dedicated runtime layer performing policy checking, capability admission, execution monitoring, rollback handling, and human override. We formalize the control boundary among the embodied agent, Embodied Capability Modules (ECMs), and runtime governance layer, and validate through 1000 randomized simulation trials across three governance dimensions. Results show 96.2% interception of unauthorized actions, reduction of unsafe continuation from 100% to 22.2% under runtime drift, and 91.4% recovery success with full policy compliance, substantially outperforming all baselines (p<0.001). By reframing runtime governance as a first-class systems problem, this paper positions policy-constrained execution as a key design principle for embodied agent systems.

Yuxi Li, Ning Xu, Wenjie Yang et al.

Modern video object segmentation (VOS) algorithms have achieved remarkably high performance in a sequential processing order, while most of currently prevailing pipelines still show some obvious inadequacy like accumulative error, unknown robustness or lack of proper interpretation tools. In this paper, we place the semi-supervised video object segmentation problem into a cyclic workflow and find the defects above can be collectively addressed via the inherent cyclic property of semi-supervised VOS systems. Firstly, a cyclic mechanism incorporated to the standard sequential flow can produce more consistent representations for pixel-wise correspondance. Relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, a simple gradient correction module, which naturally extends the offline cyclic pipeline to an online manner, can highlight the high-frequent and detailed part of results to further improve the segmentation quality while keeping feasible computation cost. Meanwhile such correction can protect the network from severe performance degration resulted from interference signals. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction process to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive comparison and detailed analysis on challenging benchmarks of DAVIS16, DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is helpful to enhance segmentation quality, improve the robustness of VOS systems, and further provide qualitative comparison and interpretation on how different VOS algorithms work. The code of this project can be found at https://github.com/lyxok1/STM-Training

Rui Qian, Yuxi Li, Huabin Liu et al.

The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relationship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to build distribution graphs, guiding the process of low-level and mid-level feature learning. We also devise a simple temporal modeling module from multi-level features to enhance motion pattern learning. Experiments demonstrate that multi-level feature optimization with the graph constraint and temporal modeling can greatly improve the representation ability in video understanding. Code is available at https://github.com/shvdiwnkozbw/Video-Representation-via-Multi-level-Optimization.

Shuyuan Li, Huabin Liu, Rui Qian et al.

Few-shot action recognition aims to recognize novel action classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradigm, which learns to compare the similarity between videos. Recently, it has been observed that directly measuring this similarity is not ideal since different action instances may show distinctive temporal distribution, resulting in severe misalignment issues across query and support videos. In this paper, we arrest this problem from two distinct aspects -- action duration misalignment and action evolution misalignment. We address them sequentially through a Two-stage Action Alignment Network (TA2N). The first stage locates the action by learning a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature (e.g. background). Next, the second stage coordinates query feature to match the spatial-temporal action evolution of support by performing temporally rearrange and spatially offset prediction. Extensive experiments on benchmark datasets show the potential of the proposed method in achieving state-of-the-art performance for few-shot action recognition.The code of this project can be found at https://github.com/R00Kie-Liu/TA2N

Kean Chen, Weiyao Lin, Jianguo Li et al.

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We provide in-depth analyses on the good convergence property and computational complexity of the proposed algorithm, both theoretically and empirically. Experimental results demonstrate notable improvement in addressing the imbalance issue in object detection over existing AP-based optimization algorithms. An improved state-of-the-art performance is achieved in one-stage detectors based on AP-loss over detectors using classification-losses on various standard benchmarks. The proposed framework is also highly versatile in accommodating different network architectures. Code is available at https://github.com/cccorn/AP-loss .

Kean Chen, Jianguo Li, Weiyao Lin et al.

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We verify good convergence property of the proposed algorithm theoretically and empirically. Experimental results demonstrate notable performance improvement in state-of-the-art one-stage detectors based on AP-loss over different kinds of classification-losses on various benchmarks, without changing the network architectures. Code is available at https://github.com/cccorn/AP-loss.

Xue Qin, Simin Luan, John See et al.

As embodied robots move toward fleet-scale operation, multi-robot coordination is becoming a central systems challenge. Existing approaches often treat this as motivation for increasing internal multi-agent decomposition within each robot. We argue for a different principle: multi-robot coordination does not require intra-robot multi-agent fragmentation. Each robot should remain a single embodied agent with its own persistent runtime, local policy scope, capability state, and recovery authority, while coordination emerges through federation across robots at the fleet level. We present Federated Single-Agent Robotics (FSAR), a runtime architecture for multi-robot coordination built on single-agent robot runtimes. Each robot exposes a governed capability surface rather than an internally fragmented agent society. Fleet coordination is achieved through shared capability registries, cross-robot task delegation, policy-aware authority assignment, trust-scoped interaction, and layered recovery protocols. We formalize key coordination relations including authority delegation, inter-robot capability requests, local-versus-fleet recovery boundaries, and hierarchical human supervision, and describe a fleet runtime architecture supporting shared Embodied Capability Module (ECM) discovery, contract-aware cross-robot coordination, and fleet-level governance. We evaluate FSAR on representative multi-robot coordination scenarios against decomposition-heavy baselines. Results show statistically significant gains in governance locality (d=2.91, p<.001 vs. centralized control) and recovery containment (d=4.88, p<.001 vs. decomposition-heavy), while reducing authority conflicts and policy violations across all scenarios. Our results support the view that the path from embodied agents to embodied fleets is better served by federation across coherent robot runtimes than by fragmentation within them.

Xue Qin, Simin Luan, John See et al.

Embodied agents increasingly rely on modular capabilities that can be installed, upgraded, composed, and governed at runtime. Prior work has introduced embodied capability modules (ECMs) as reusable units of embodied functionality, and recent research has explored their runtime governance and controlled evolution. However, a key systems question remains unresolved: how can ECMs be composed and released as a stable software ecosystem rather than as ad hoc skill bundles? We present ECM Contracts, a contract-based interface model for embodied capability modules. Unlike conventional software interfaces that specify only input and output types, ECM Contracts encode six dimensions essential for embodied execution: functional signature, behavioral assumptions, resource requirements, permission boundaries, recovery semantics, and version compatibility. Based on this model, we introduce a compatibility framework for ECM installation, composition, and upgrade, enabling static and pre-deployment checks for type mismatches, dependency conflicts, policy violations, resource contention, and recovery incompatibilities. We further propose a release discipline for embodied capabilities, including version-aware compatibility classes, deprecation rules, migration constraints, and policy-sensitive upgrade checks. We implement a prototype ECM registry, resolver, and contract checker, and evaluate the approach on modular embodied tasks in a robotics runtime setting. Results show that contract-aware composition substantially reduces unsafe or invalid module combinations, and that contract-guided release checks improve upgrade safety and rollback readiness compared with schema-only or ad hoc baselines. Our findings suggest that stable embodied software ecosystems require more than modular packaging: they require explicit contracts that connect capability composition, governance, and evolution.

Xue Qin, Simin Luan, John See et al.

Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation accuracy. These metrics leave a critical gap: they do not measure whether embodied systems are governable -- whether they respect capability boundaries, enforce policies, recover safely, maintain audit trails, and respond to human oversight. We present EmbodiedGovBench, a benchmark for governance-oriented evaluation of embodied agent systems. Rather than asking only whether a robot can complete a task, EmbodiedGovBench evaluates whether the system remains controllable, policy-bounded, recoverable, auditable, and evolution-safe under realistic perturbations. The benchmark covers seven governance dimensions: unauthorized capability invocation, runtime drift robustness, recovery success, policy portability, version upgrade safety, human override responsiveness, and audit completeness. We define a benchmark structure spanning single-robot and fleet settings, with scenario templates, perturbation operators, governance metrics, and baseline evaluation protocols. We describe how the benchmark can be instantiated over embodied capability runtimes with modular interfaces and contract-aware upgrade workflows. Our analysis suggests that embodied governance should become a first-class evaluation target. EmbodiedGovBench provides the initial measurement framework for that shift.

Xue Qin, Simin Luan, John See et al.

Skill libraries in deployed robotic systems are continually updated through fine-tuning, fresh demonstrations, or domain adaptation, yet existing typed-composition methods (BLADE, SymSkill, Generative Skill Chaining) treat the library as frozen at test time and do not analyze how composition outcomes change when a skill is replaced. We introduce a paired-sampling cross-version swap protocol on robosuite manipulation tasks to characterize this dimension of compositional skill learning. On a dual-arm peg-in-hole task we discover a dominant-skill effect: one ECM achieves 86.7% atomic success rate while every other ECM is at or below 26.7%, and whether this dominant ECM enters a composition shifts the success rate by up to +50pp. We characterize the boundary on a simpler pick task where all atomic policies saturate at 100% and the effect is undefined. Across three tasks we further find that off-policy behavioral distance metrics fail to identify the dominant ECM, ruling out the natural cheap predictor. We propose an atomic-quality probe and a Hybrid Selector combining per-skill probes (zero per-decision cost) with selective composition revalidation (full cost), and characterize its Pareto frontier on 144 skill-update decisions. On T6 the atomic-only probe sits 23pp below full revalidation (64.6% vs 87.5% oracle match) at zero per-decision cost; a Hybrid Selector with m=10 closes most of that gap to ~12pp at 46% of full-revalidation cost. On the cross-task average over 144 events, atomic-only is within 3pp of full revalidation under a mixed-oracle caveat. The atomic-quality probe is, to our knowledge, the first principled, deployment-ready primitive for skill-update governance in compositional robot policies.

Tieyuan Chen, Huabin Liu, Chern Hong Lim et al.

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex than image data because it requires learning and preserving both spatial appearance and temporal action involvement. To address this challenge, we propose a novel exemplar-free framework that equips separate spatiotemporal adapters to learn new class patterns, accommodating the incremental information representation requirements unique to each class. While separate adapters are proven to mitigate forgetting and fit unique requirements, naively applying them hinders the intrinsic connection between spatial and temporal information increments, affecting the efficiency of representing newly learned class information. Motivated by this, we introduce two key innovations from a causal perspective. First, a causal distillation module is devised to maintain the relation between spatial-temporal knowledge for a more efficient representation. Second, a causal compensation mechanism is proposed to reduce the conflicts during increment and memorization between different types of information. Extensive experiments conducted on benchmark datasets demonstrate that our framework can achieve new state-of-the-art results, surpassing current example-based methods by 4.2% in accuracy on average.

Shuwei Guo, Simin Luan, Yan Ke et al.

Moiré patterns arise from spectral aliasing between display pixel lattices and camera sensor grids, manifesting as anisotropic, multi-scale artifacts that pose significant challenges for digital image demoiréing. We propose MoiréNet, a convolutional neural U-Net-based framework that synergistically integrates frequency and spatial domain features for effective artifact removal. MoiréNet introduces two key components: a Directional Frequency-Spatial Encoder (DFSE) that discerns moiré orientation via directional difference convolution, and a Frequency-Spatial Adaptive Selector (FSAS) that enables precise, feature-adaptive suppression. Extensive experiments demonstrate that MoiréNet achieves state-of-the-art performance on public and actively used datasets while being highly parameter-efficient. With only 5.513M parameters, representing a 48% reduction compared to ESDNet-L, MoiréNet combines superior restoration quality with parameter efficiency, making it well-suited for resource-constrained applications including smartphone photography, industrial imaging, and augmented reality.

Xianbao Hou, Yonghao He, Zeyd Boukhers et al.

Acquiring high-quality instance segmentation data is challenging due to the labor-intensive nature of the annotation process and significant class imbalances within datasets. Recent studies have utilized the integration of Copy-Paste and diffusion models to create more diverse datasets. However, these studies often lack deep collaboration between large language models (LLMs) and diffusion models, and underutilize the rich information within the existing training data. To address these limitations, we propose InstaDA, a novel, training-free Dual-Agent system designed to augment instance segmentation datasets. First, we introduce a Text-Agent (T-Agent) that enhances data diversity through collaboration between LLMs and diffusion models. This agent features a novel Prompt Rethink mechanism, which iteratively refines prompts based on the generated images. This process not only fosters collaboration but also increases image utilization and optimizes the prompts themselves. Additionally, we present an Image-Agent (I-Agent) aimed at enriching the overall data distribution. This agent augments the training set by generating new instances conditioned on the training images. To ensure practicality and efficiency, both agents operate as independent and automated workflows, enhancing usability. Experiments conducted on the LVIS 1.0 validation set indicate that InstaDA achieves significant improvements, with an increase of +4.0 in box average precision (AP) and +3.3 in mask AP compared to the baseline. Furthermore, it outperforms the leading model, DiverGen, by +0.3 in box AP and +0.1 in mask AP, with a notable +0.7 gain in box AP on common categories and mask AP gains of +0.2 on common categories and +0.5 on frequent categories.

Shiyuan Chen, Wei Sui, Bohao Zhang et al.

Camera-based 3D semantic scene completion (SSC) provides dense geometric and semantic perception for autonomous driving and robotic navigation. However, existing methods rely on a coupled encoder to deliver both semantic and geometric priors, which forces the model to make a trade-off between conflicting demands and limits its overall performance. To tackle these challenges, we propose FoundationSSC, a novel framework that performs dual decoupling at both the source and pathway levels. At the source level, we introduce a foundation encoder that provides rich semantic feature priors for the semantic branch and high-fidelity stereo cost volumes for the geometric branch. At the pathway level, these priors are refined through specialised, decoupled pathways, yielding superior semantic context and depth distributions. Our dual-decoupling design produces disentangled and refined inputs, which are then utilised by a hybrid view transformation to generate complementary 3D features. Additionally, we introduce a novel Axis-Aware Fusion (AAF) module that addresses the often-overlooked challenge of fusing these features by anisotropically merging them into a unified representation. Extensive experiments demonstrate the advantages of FoundationSSC, achieving simultaneous improvements in both semantic and geometric metrics, surpassing prior bests by +0.23 mIoU and +2.03 IoU on SemanticKITTI. Additionally, we achieve state-of-the-art performance on SSCBench-KITTI-360, with 21.78 mIoU and 48.61 IoU. The code will be released upon acceptance.

Xinqi Fan, Jingting Li, John See et al.

Facial micro-expressions (MEs) are involuntary movements of the face that occur spontaneously when a person experiences an emotion but attempts to suppress or repress the facial expression, typically found in a high-stakes environment. In recent years, substantial advancements have been made in the areas of ME recognition, spotting, and generation. However, conventional approaches that treat spotting and recognition as separate tasks are suboptimal, particularly for analyzing long-duration videos in realistic settings. Concurrently, the emergence of multimodal large language models (MLLMs) and large vision-language models (LVLMs) offers promising new avenues for enhancing ME analysis through their powerful multimodal reasoning capabilities. The ME grand challenge (MEGC) 2025 introduces two tasks that reflect these evolving research directions: (1) ME spot-then-recognize (ME-STR), which integrates ME spotting and subsequent recognition in a unified sequential pipeline; and (2) ME visual question answering (ME-VQA), which explores ME understanding through visual question answering, leveraging MLLMs or LVLMs to address diverse question types related to MEs. All participating algorithms are required to run on this test set and submit their results on a leaderboard. More details are available at https://megc2025.github.io.

Huabin Liu, Weiyao Lin, Tieyuan Chen et al.

Current few-shot action recognition involves two primary sources of information for classification:(1) intra-video information, determined by frame content within a single video clip, and (2) inter-video information, measured by relationships (e.g., feature similarity) among videos. However, existing methods inadequately exploit these two information sources. In terms of intra-video information, current sampling operations for input videos may omit critical action information, reducing the utilization efficiency of video data. For the inter-video information, the action misalignment among videos makes it challenging to calculate precise relationships. Moreover, how to jointly consider both inter- and intra-video information remains under-explored for few-shot action recognition. To this end, we propose a novel framework, Video Information Maximization (VIM), for few-shot video action recognition. VIM is equipped with an adaptive spatial-temporal video sampler and a spatiotemporal action alignment model to maximize intra- and inter-video information, respectively. The video sampler adaptively selects important frames and amplifies critical spatial regions for each input video based on the task at hand. This preserves and emphasizes informative parts of video clips while eliminating interference at the data level. The alignment model performs temporal and spatial action alignment sequentially at the feature level, leading to more precise measurements of inter-video similarity. Finally, These goals are facilitated by incorporating additional loss terms based on mutual information measurement. Consequently, VIM acts to maximize the distinctiveness of video information from limited video data. Extensive experimental results on public datasets for few-shot action recognition demonstrate the effectiveness and benefits of our framework.

Rui Qian, Weiyao Lin, John See et al.

This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to bias to static background and have difficulty establishing global temporal structures. The major reason is that the positive pairs, i.e., different clips sampled from the same video, have limited temporal receptive field, and usually share similar background but differ in motions. To address these problems, we propose a framework to jointly utilize local clips and global videos to learn from detailed region-level correspondence as well as general long-term temporal relations. Based on a set of controllable augmentations, we achieve accurate appearance and motion pattern alignment through soft spatio-temporal region contrast. Our formulation is able to avoid the low-level redundancy shortcut by mutual information minimization to improve the generalization. We also introduce local-global temporal order dependency to further bridge the gap between clip-level and video-level representations for robust temporal modeling. Extensive experiments demonstrate that our framework is superior on three video benchmarks in action recognition and video retrieval, capturing more accurate temporal dynamics.

Gen-Bing Liong, John See, Lai-Kuan Wong

Facial expressions vary from the visible to the subtle. In recent years, the analysis of micro-expressions $-$ a natural occurrence resulting from the suppression of one's true emotions, has drawn the attention of researchers with a broad range of potential applications. However, spotting microexpressions in long videos becomes increasingly challenging when intertwined with normal or macro-expressions. In this paper, we propose a shallow optical flow three-stream CNN (SOFTNet) model to predict a score that captures the likelihood of a frame being in an expression interval. By fashioning the spotting task as a regression problem, we introduce pseudo-labeling to facilitate the learning process. We demonstrate the efficacy and efficiency of the proposed approach on the recent MEGC 2020 benchmark, where state-of-the-art performance is achieved on CAS(ME)$^{2}$ with equally promising results on SAMM Long Videos.

Yuang Zhang, Huanyu He, Jianguo Li et al.

Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods. In this paper, we develop a unique perspective of pedestrian detection as a variational inference problem. We formulate a novel and efficient algorithm for pedestrian detection by modeling the dense proposals as a latent variable while proposing a customized Auto Encoding Variational Bayes (AEVB) algorithm. Through the optimization of our proposed algorithm, a classical detector can be fashioned into a variational pedestrian detector. Experiments conducted on CrowdHuman and CityPersons datasets show that the proposed algorithm serves as an efficient solution to handle the dense pedestrian detection problem for the case of single-stage detectors. Our method can also be flexibly applied to two-stage detectors, achieving notable performance enhancement.

Yuxi Li, Ning Xu, Jinlong Peng et al.

In this paper, we address several inadequacies of current video object segmentation pipelines. Firstly, a cyclic mechanism is incorporated to the standard semi-supervised process to produce more robust representations. By relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, we introduce a simple gradient correction module, which extends the offline pipeline to an online method while maintaining the efficiency of the former. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive experiments on challenging benchmarks of DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is beneficial to segmentation quality.

Weiyao Lin, Xiaoyi He, Wenrui Dai et al.

Feature coding has been recently considered to facilitate intelligent video analysis for urban computing. Instead of raw videos, extracted features in the front-end are encoded and transmitted to the back-end for further processing. In this article, we present a lossless key-point sequence compression approach for efficient feature coding. The essence of this predict-and-encode strategy is to eliminate the spatial and temporal redundancies of key points in videos. Multiple prediction modes with an adaptive mode selection method are proposed to handle key-point sequences with various structures and motion. Experimental results validate the effectiveness of the proposed scheme on four types of widely used key-point sequences in video analysis.

Yuxi Li, Weiyao Lin, Tao Wang et al.

The task of spatial-temporal action detection has attracted increasing attention among researchers. Existing dominant methods solve this problem by relying on short-term information and dense serial-wise detection on each individual frames or clips. Despite their effectiveness, these methods showed inadequate use of long-term information and are prone to inefficiency. In this paper, we propose for the first time, an efficient framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner. There are two key characteristics in this framework: (1) Both long-term and short-term sampled information are explicitly utilized in our spatiotemporal network, (2) A new dynamic feature sampling module (DTS) is designed to effectively approximate the tube output while keeping the system tractable. We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets, achieving promising results that are competitive to state-of-the-art methods. The proposed sparse-to-dense strategy rendered our framework about 7.6 times more efficient than the nearest competitor.

Yuxi Li, Weiyao Lin, John See et al.

Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization. In this paper, we propose Coarse-to-Fine Action Detector (CFAD),an original end-to-end trainable framework for efficient spatio-temporal action localization. The CFAD introduces a new paradigm that first estimates coarse spatio-temporal action tubes from video streams, and then refines the tubes' location based on key timestamps. This concept is implemented by two key components, the Coarse and Refine Modules in our framework. The parameterized modeling of long temporal information in the Coarse Module helps obtain accurate initial tube estimation, while the Refine Module selectively adjusts the tube location under the guidance of key timestamps. Against other methods, theproposed CFAD achieves competitive results on action detection benchmarks of UCF101-24, UCFSports and JHMDB-21 with inference speed that is 3.3x faster than the nearest competitors.

Zhiming Chen, Kean Chen, Weiyao Lin et al.

Object detection using an oriented bounding box (OBB) can better target rotated objects by reducing the overlap with background areas. Existing OBB approaches are mostly built on horizontal bounding box detectors by introducing an additional angle dimension optimized by a distance loss. However, as the distance loss only minimizes the angle error of the OBB and that it loosely correlates to the IoU, it is insensitive to objects with high aspect ratios. Therefore, a novel loss, Pixels-IoU (PIoU) Loss, is formulated to exploit both the angle and IoU for accurate OBB regression. The PIoU loss is derived from IoU metric with a pixel-wise form, which is simple and suitable for both horizontal and oriented bounding box. To demonstrate its effectiveness, we evaluate the PIoU loss on both anchor-based and anchor-free frameworks. The experimental results show that PIoU loss can dramatically improve the performance of OBB detectors, particularly on objects with high aspect ratios and complex backgrounds. Besides, previous evaluation datasets did not include scenarios where the objects have high aspect ratios, hence a new dataset, Retail50K, is introduced to encourage the community to adapt OBB detectors for more complex environments.

Weiyao Lin, Xiaoyi He, Xintong Han et al.

This paper addresses neural network based post-processing for the state-of-the-art video coding standard, High Efficiency Video Coding (HEVC). We first propose a partition-aware Convolution Neural Network (CNN) that utilizes the partition information produced by the encoder to assist in the post-processing. In contrast to existing CNN-based approaches, which only take the decoded frame as input, the proposed approach considers the coding unit (CU) size information and combines it with the distorted decoded frame such that the artifacts introduced by HEVC are efficiently reduced. We further introduce an adaptive-switching neural network (ASN) that consists of multiple independent CNNs to adaptively handle the variations in content and distortion within compressed-video frames, providing further reduction in visual artifacts. Additionally, an iterative training procedure is proposed to train these independent CNNs attentively on different local patch-wise classes. Experiments on benchmark sequences demonstrate the effectiveness of our partition-aware and adaptive-switching neural networks. The source code can be found at http://min.sjtu.edu.cn/lwydemo/HEVCpostprocessing.html.

Weiyao Lin, Yuxi Li, Hao Xiao et al.

The task of re-identifying groups of people underdifferent camera views is an important yet less-studied problem.Group re-identification (Re-ID) is a very challenging task sinceit is not only adversely affected by common issues in traditionalsingle object Re-ID problems such as viewpoint and human posevariations, but it also suffers from changes in group layout andgroup membership. In this paper, we propose a novel conceptof group granularity by characterizing a group image by multi-grained objects: individual persons and sub-groups of two andthree people within a group. To achieve robust group Re-ID,we first introduce multi-grained representations which can beextracted via the development of two separate schemes, i.e. onewith hand-crafted descriptors and another with deep neuralnetworks. The proposed representation seeks to characterize bothappearance and spatial relations of multi-grained objects, and isfurther equipped with importance weights which capture varia-tions in intra-group dynamics. Optimal group-wise matching isfacilitated by a multi-order matching process which in turn,dynamically updates the importance weights in iterative fashion.We evaluated on three multi-camera group datasets containingcomplex scenarios and large dynamics, with experimental resultsdemonstrating the effectiveness of our approach. The published dataset can be found in \url{http://min.sjtu.edu.cn/lwydemo/GroupReID.html}

Sze-Teng Liong, Y. S. Gan, John See et al.

In the recent year, state-of-the-art for facial micro-expression recognition have been significantly advanced by deep neural networks. The robustness of deep learning has yielded promising performance beyond that of traditional handcrafted approaches. Most works in literature emphasized on increasing the depth of networks and employing highly complex objective functions to learn more features. In this paper, we design a Shallow Triple Stream Three-dimensional CNN (STSTNet) that is computationally light whilst capable of extracting discriminative high level features and details of micro-expressions. The network learns from three optical flow features (i.e., optical strain, horizontal and vertical optical flow fields) computed based on the onset and apex frames of each video. Our experimental results demonstrate the effectiveness of the proposed STSTNet, which obtained an unweighted average recall rate of 0.7605 and unweighted F1-score of 0.7353 on the composite database consisting of 442 samples from the SMIC, CASME II and SAMM databases.

Yee-Hui Oh, John See, Anh Cat Le Ngo et al.

Over the last few years, automatic facial micro-expression analysis has garnered increasing attention from experts across different disciplines because of its potential applications in various fields such as clinical diagnosis, forensic investigation and security systems. Advances in computer algorithms and video acquisition technology have rendered machine analysis of facial micro-expressions possible today, in contrast to decades ago when it was primarily the domain of psychiatrists where analysis was largely manual. Indeed, although the study of facial micro-expressions is a well-established field in psychology, it is still relatively new from the computational perspective with many interesting problems. In this survey, we present a comprehensive review of state-of-the-art databases and methods for micro-expressions spotting and recognition. Individual stages involved in the automation of these tasks are also described and reviewed at length. In addition, we also deliberate on the challenges and future directions in this growing field of automatic facial micro-expression analysis.

Huai-Qian Khor, John See, Raphael C. W. Phan et al.

Facial micro-expression (ME) recognition has posed a huge challenge to researchers for its subtlety in motion and limited databases. Recently, handcrafted techniques have achieved superior performance in micro-expression recognition but at the cost of domain specificity and cumbersome parametric tunings. In this paper, we propose an Enriched Long-term Recurrent Convolutional Network (ELRCN) that first encodes each micro-expression frame into a feature vector through CNN module(s), then predicts the micro-expression by passing the feature vector through a Long Short-term Memory (LSTM) module. The framework contains two different network variants: (1) Channel-wise stacking of input data for spatial enrichment, (2) Feature-wise stacking of features for temporal enrichment. We demonstrate that the proposed approach is able to achieve reasonably good performance, without data augmentation. In addition, we also present ablation studies conducted on the framework and visualizations of what CNN "sees" when predicting the micro-expression classes.

Huai-Qian Khor, John See

Video surveillance is a well researched area of study with substantial work done in the aspects of object detection, tracking and behavior analysis. With the abundance of video data captured over a long period of time, we can understand patterns in human behavior and scene dynamics through data-driven temporal analytics. In this work, we propose two schemes to perform descriptive and predictive analytics on long-term video surveillance data. We generate heatmap and footmap visualizations to describe spatially pooled trajectory patterns with respect to time and location. We also present two approaches for anomaly prediction at the day-level granularity: a trajectory-based statistical approach, and a time-series based approach. Experimentation with one year data from a single camera demonstrates the ability to uncover interesting insights about the scene and to predict anomalies reasonably well.

Sze-Teng Liong, John See, Raphael Chung-Wei Phan et al.

Optical strain is an extension of optical flow that is capable of quantifying subtle changes on faces and representing the minute facial motion intensities at the pixel level. This is computationally essential for the relatively new field of spontaneous micro-expression, where subtle expressions can be technically challenging to pinpoint. In this paper, we present a novel method for detecting and recognizing micro-expressions by utilizing facial optical strain magnitudes to construct optical strain features and optical strain weighted features. The two sets of features are then concatenated to form the resultant feature histogram. Experiments were performed on the CASME II and SMIC databases. We demonstrate on both databases, the usefulness of optical strain information and more importantly, that our best approaches are able to outperform the original baseline results for both detection and recognition tasks. A comparison of the proposed method with other existing spatio-temporal feature extraction approaches is also presented.

Sze-Teng Liong, John See, KokSheik Wong et al.

Despite recent interest and advances in facial micro-expression research, there is still plenty room for improvement in terms of micro-expression recognition. Conventional feature extraction approaches for micro-expression video consider either the whole video sequence or a part of it, for representation. However, with the high-speed video capture of micro-expressions (100-200 fps), are all frames necessary to provide a sufficiently meaningful representation? Is the luxury of data a bane to accurate recognition? A novel proposition is presented in this paper, whereby we utilize only two images per video: the apex frame and the onset frame. The apex frame of a video contains the highest intensity of expression changes among all frames, while the onset is the perfect choice of a reference frame with neutral expression. A new feature extractor, Bi-Weighted Oriented Optical Flow (Bi-WOOF) is proposed to encode essential expressiveness of the apex frame. We evaluated the proposed method on five micro-expression databases: CAS(ME)$^2$, CASME II, SMIC-HS, SMIC-NIR and SMIC-VIS. Our experiments lend credence to our hypothesis, with our proposed technique achieving a state-of-the-art F1-score recognition performance of 61% and 62% in the high frame rate CASME II and SMIC-HS databases respectively.

Anh Cat Le Ngo, John See, Raphael Chung-Wei Phan

Spontaneous subtle emotions are expressed through micro-expressions, which are tiny, sudden and short-lived dynamics of facial muscles; thus poses a great challenge for visual recognition. The abrupt but significant dynamics for the recognition task are temporally sparse while the rest, irrelevant dynamics, are temporally redundant. In this work, we analyze and enforce sparsity constrains to learn significant temporal and spectral structures while eliminate irrelevant facial dynamics of micro-expressions, which would ease the challenge in the visual recognition of spontaneous subtle emotions. The hypothesis is confirmed through experimental results of automatic spontaneous subtle emotion recognition with several sparsity levels on CASME II and SMIC, the only two publicly available spontaneous subtle emotion databases. The overall performances of the automatic subtle emotion recognition are boosted when only significant dynamics are preserved from the original sequences.