arXiv subjects

Angela Yao

Publications and source records attributed to Angela Yao.

At least 55 records · Page 3Linked to original sources

arXiv2025

Demographic Inference from Social Media Data with Multimodal Foundation Models: Strategies, Evaluation, and Benchmarking

Demographic inference plays a crucial role in understanding the representativeness and equity of social media-based research. However, existing methods typically rely on a single modality, such as text, image, or network, and are limited to predicting one or two demographic attributes, constraining their generalizability and robustness across populations. This study leverages GPT-5, a state-of-the-art multimodal foundation model, to infer age, gender, and race from social media profiles. Using a dataset of 263 publicly available X (formerly Twitter) users, we design a progressive multimodal framework that incrementally incorporates usernames, profile descriptions, tweets, and profile images to examine how each information source contributes to inference accuracy. Results show a consistent improvement across all conditions, with the inclusion of textual and visual cues substantially enhancing performance. GPT-5 achieves an overall accuracy of 0.90 for age, 0.98 for gender, and 0.85 for race, outperforming existing models under equivalent inputs. These findings demonstrate the potential of large multimodal foundation models to capture complex, cross-modal demographic cues with minimal task-specific training. The study further highlights a transparent, interpretable approach to multimodal reasoning that advances the accuracy, fairness, and scalability of demographic inference in social data analytics.

cs.SI↗

arXiv2025

AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation

Optimization-based text-to-3D methods distill guidance from 2D generative models via Score Distillation Sampling (SDS), but implicitly treat this guidance as static. This work shows that ignoring source dynamics yields inconsistent trajectories that suppress or merge semantic cues, leading to "semantic over-smoothing" artifacts. As such, we reformulate text-to-3D optimization as mapping a dynamically evolving source distribution to a fixed target distribution. We cast the problem into a dual-conditioned latent space, conditioned on both the text prompt and the intermediately rendered image. Given this joint setup, we observe that the image condition naturally anchors the current source distribution. Building on this insight, we introduce AnchorDS, an improved score distillation mechanism that provides state-anchored guidance with image conditions and stabilizes generation. We further penalize erroneous source estimates and design a lightweight filter strategy and fine-tuning strategy that refines the anchor with negligible overhead. AnchorDS produces finer-grained detail, more natural colours, and stronger semantic consistency, particularly for complex prompts, while maintaining efficiency. Extensive experiments show that our method surpasses previous methods in both quality and efficiency.

cs.LG↗

arXiv2025

EgoBlind: Towards Egocentric Visual Assistance for the Blind

We present EgoBlind, the first egocentric VideoQA dataset collected from blind individuals to evaluate the assistive capabilities of contemporary multimodal large language models (MLLMs). EgoBlind comprises 1,392 first-person videos from the daily lives of blind and visually impaired individuals. It also features 5,311 questions directly posed or verified by the blind to reflect their in-situation needs for visual assistance. Each question has an average of 3 manually annotated reference answers to reduce subjectiveness. Using EgoBlind, we comprehensively evaluate 16 advanced MLLMs and find that all models struggle. The best performers achieve an accuracy near 60\%, which is far behind human performance of 87.4\%. To guide future advancements, we identify and summarize major limitations of existing MLLMs in egocentric visual assistance for the blind and explore heuristic solutions for improvement. With these efforts, we hope that EgoBlind will serve as a foundation for developing effective AI assistants to enhance the independence of the blind and visually impaired. Data and code are available at https://github.com/doc-doc/EgoBlind.

cs.CV↗

arXiv2025

REAR: Rethinking Visual Autoregressive Models via Generator-Tokenizer Consistency Regularization

Visual autoregressive (AR) generation offers a promising path toward unifying vision and language models, yet its performance remains suboptimal against diffusion models. Prior work often attributes this gap to tokenizer limitations and rasterization ordering. In this work, we identify a core bottleneck from the perspective of generator-tokenizer inconsistency, i.e., the AR-generated tokens may not be well-decoded by the tokenizer. To address this, we propose reAR, a simple training strategy introducing a token-wise regularization objective: when predicting the next token, the causal transformer is also trained to recover the visual embedding of the current token and predict the embedding of the target token under a noisy context. It requires no changes to the tokenizer, generation order, inference pipeline, or external models. Despite its simplicity, reAR substantially improves performance. On ImageNet, it reduces gFID from 3.02 to 1.86 and improves IS to 316.9 using a standard rasterization-based tokenizer. When applied to advanced tokenizers, it achieves a gFID of 1.42 with only 177M parameters, matching the performance with larger state-of-the-art diffusion models (675M).

cs.CV↗

arXiv2025

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets. To further improve the performance of synthetic datasets, various training pipelines and optimization objectives have been proposed, greatly advancing the field of dataset distillation. Recent decoupled dataset distillation methods introduce soft labels and stronger data augmentation during the post-evaluation phase and scale dataset distillation up to larger datasets (e.g., ImageNet-1K). However, this raises a question: Is accuracy still a reliable metric to fairly evaluate dataset distillation methods? Our empirical findings suggest that the performance improvements of these methods often stem from additional techniques rather than the inherent quality of the images themselves, with even randomly sampled images achieving superior results. Such misaligned evaluation settings severely hinder the development of DD. Therefore, we propose DD-Ranking, a unified evaluation framework, along with new general evaluation metrics to uncover the true performance improvements achieved by different methods. By refocusing on the actual information enhancement of distilled datasets, DD-Ranking provides a more comprehensive and fair evaluation standard for future research advancements.

cs.CV↗

arXiv2025

Leveraging RGB Images for Pre-Training of Event-Based Hand Pose Estimation

This paper presents RPEP, the first pre-training method for event-based 3D hand pose estimation using labeled RGB images and unpaired, unlabeled event data. Event data offer significant benefits such as high temporal resolution and low latency, but their application to hand pose estimation is still limited by the scarcity of labeled training data. To address this, we repurpose real RGB datasets to train event-based estimators. This is done by constructing pseudo-event-RGB pairs, where event data is generated and aligned with the ground-truth poses of RGB images. Unfortunately, existing pseudo-event generation techniques assume stationary objects, thus struggling to handle non-stationary, dynamically moving hands. To overcome this, RPEP introduces a novel generation strategy that decomposes hand movements into smaller, step-by-step motions. This decomposition allows our method to capture temporal changes in articulation, constructing more realistic event data for a moving hand. Additionally, RPEP imposes a motion reversal constraint, regularizing event generation using reversed motion. Extensive experiments show that our pre-trained model significantly outperforms state-of-the-art methods on real event data, achieving up to 24% improvement on EvRealHands. Moreover, it delivers strong performance with minimal labeled samples for fine-tuning, making it well-suited for practical deployment.

cs.CV↗

arXiv2025

InstructHumans: Editing Animated 3D Human Textures with Instructions

We present InstructHumans, a novel framework for instruction-driven {animatable} 3D human texture editing. Existing text-based 3D editing methods often directly apply Score Distillation Sampling (SDS). SDS, designed for generation tasks, cannot account for the defining requirement of editing -- maintaining consistency with the source avatar. This work shows that naively using SDS harms editing, as it may destroy consistency. We propose a modified SDS for Editing (SDS-E) that selectively incorporates subterms of SDS across diffusion timesteps. We further enhance SDS-E with spatial smoothness regularization and gradient-based viewpoint sampling for edits with sharp and high-fidelity detailing. Incorporating SDS-E into a 3D human texture editing framework allows us to outperform existing 3D editing methods. Our avatars faithfully reflect the textual edits while remaining consistent with the original avatars. Project page: https://jyzhu.top/instruct-humans/.

cs.CV↗

arXiv2025

Improving Human Motion Plausibility with Body Momentum

Many studies decompose human motion into local motion in a frame attached to the root joint and global motion of the root joint in the world frame, treating them separately. However, these two components are not independent. Global movement arises from interactions with the environment, which are, in turn, driven by changes in the body configuration. Motion models often fail to precisely capture this physical coupling between local and global dynamics, while deriving global trajectories from joint torques and external forces is computationally expensive and complex. To address these challenges, we propose using whole-body linear and angular momentum as a constraint to link local motion with global movement. Since momentum reflects the aggregate effect of joint-level dynamics on the body's movement through space, it provides a physically grounded way to relate local joint behavior to global displacement. Building on this insight, we introduce a new loss term that enforces consistency between the generated momentum profiles and those observed in ground-truth data. Incorporating our loss reduces foot sliding and jitter, improves balance, and preserves the accuracy of the recovered motion. Code and data are available at the project page https://hlinhn.github.io/momentum_bmvc.

cs.CV↗

arXiv2025

BERT4Traj: Transformer Based Trajectory Reconstruction for Sparse Mobility Data

Understanding human mobility is essential for applications in public health, transportation, and urban planning. However, mobility data often suffers from sparsity due to limitations in data collection methods, such as infrequent GPS sampling or call detail record (CDR) data that only capture locations during communication events. To address this challenge, we propose BERT4Traj, a transformer based model that reconstructs complete mobility trajectories by predicting hidden visits in sparse movement sequences. Inspired by BERT's masked language modeling objective and self_attention mechanisms, BERT4Traj leverages spatial embeddings, temporal embeddings, and contextual background features such as demographics and anchor points. We evaluate BERT4Traj on real world CDR and GPS datasets collected in Kampala, Uganda, demonstrating that our approach significantly outperforms traditional models such as Markov Chains, KNN, RNNs, and LSTMs. Our results show that BERT4Traj effectively reconstructs detailed and continuous mobility trajectories, enhancing insights into human movement patterns.

cs.LG↗

arXiv2025

VideoQA in the Era of LLMs: An Empirical Study

Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks. As a golden testbed, Video Question Answering (VideoQA) plays pivotal role in Video-LLM developing. This work conducts a timely and comprehensive study of Video-LLMs' behavior in VideoQA, aiming to elucidate their success and failure modes, and provide insights towards more human-like video understanding and question answering. Our analyses demonstrate that Video-LLMs excel in VideoQA; they can correlate contextual cues and generate plausible responses to questions about varied video contents. However, models falter in handling video temporality, both in reasoning about temporal content ordering and grounding QA-relevant temporal moments. Moreover, the models behave unintuitively - they are unresponsive to adversarial video perturbations while being sensitive to simple variations of candidate answers and questions. Also, they do not necessarily generalize better. The findings demonstrate Video-LLMs' QA capability in standard condition yet highlight their severe deficiency in robustness and interpretability, suggesting the urgent need on rationales in Video-LLM developing.

cs.CV↗

arXiv2025

TIGeR: Text-Instructed Generation and Refinement for Template-Free Hand-Object Interaction

Pre-defined 3D object templates are widely used in 3D reconstruction of hand-object interactions. However, they often require substantial manual efforts to capture or source, and inherently restrict the adaptability of models to unconstrained interaction scenarios, e.g., heavily-occluded objects. To overcome this bottleneck, we propose a new Text-Instructed Generation and Refinement (TIGeR) framework, harnessing the power of intuitive text-driven priors to steer the object shape refinement and pose estimation. We use a two-stage framework: a text-instructed prior generation and vision-guided refinement. As the name implies, we first leverage off-the-shelf models to generate shape priors according to the text description without tedious 3D crafting. Considering the geometric gap between the synthesized prototype and the real object interacted with the hand, we further calibrate the synthesized prototype via 2D-3D collaborative attention. TIGeR achieves competitive performance, i.e., 1.979 and 5.468 object Chamfer distance on the widely-used Dex-YCB and Obman datasets, respectively, surpassing existing template-free methods. Notably, the proposed framework shows robustness to occlusion, while maintaining compatibility with heterogeneous prior sources, e.g., retrieved hand-crafted prototypes, in practical deployment scenarios.

cs.CV↗

arXiv2025

Semantics-aware Test-time Adaptation for 3D Human Pose Estimation

This work highlights a semantics misalignment in 3D human pose estimation. For the task of test-time adaptation, the misalignment manifests as overly smoothed and unguided predictions. The smoothing settles predictions towards some average pose. Furthermore, when there are occlusions or truncations, the adaptation becomes fully unguided. To this end, we pioneer the integration of a semantics-aware motion prior for the test-time adaptation of 3D pose estimation. We leverage video understanding and a well-structured motion-text space to adapt the model motion prediction to adhere to video semantics during test time. Additionally, we incorporate a missing 2D pose completion based on the motion-text similarity. The pose completion strengthens the motion prior's guidance for occlusions and truncations. Our method significantly improves state-of-the-art 3D human pose estimation TTA techniques, with more than 12% decrease in PA-MPJPE on 3DPW and 3DHP.

cs.CV↗

arXiv2025

Scene-Text Grounding for Text-Based Video Question Answering

Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decisionmaking and heavy reliance on scene-text recognition. In this paper, we propose to study Grounded TextVideoQA by forcing models to answer questions and spatio-temporally localize the relevant scene-text regions, thus decoupling QA from scenetext recognition and promoting research towards interpretable QA. The task has three-fold significance. First, it encourages scene-text evidence versus other short-cuts for answer predictions. Second, it directly accepts scene-text regions as visual answers, thus circumventing the problem of ineffective answer evaluation by stringent string matching. Third, it isolates the challenges inherited in VideoQA and scene-text recognition. This enables the diagnosis of the root causes for failure predictions, e.g., wrong QA or wrong scene-text recognition? To achieve Grounded TextVideoQA, we propose the T2S-QA model that highlights a disentangled temporal-to-spatial contrastive learning strategy for weakly-supervised scene-text grounding and grounded TextVideoQA. To facilitate evaluation, we construct a new dataset ViTXT-GQA which features 52K scene-text bounding boxes within 2.2K temporal segments related to 2K questions and 729 videos. With ViTXT-GQA, we perform extensive experiments and demonstrate the severe limitations of existing techniques in Grounded TextVideoQA. While T2S-QA achieves superior results, the large performance gap with human leaves ample space for improvement. Our further analysis of oracle scene-text inputs posits that the major challenge is scene-text recognition. To advance the research of Grounded TextVideoQA, our dataset and code are at https://github.com/zhousheng97/ViTXT-GQA.git

cs.CV↗

arXiv2025

Question-Answering Dense Video Events

This paper presents question-answering on dense video events, a novel task that answers and grounds dense-event questions in long videos, thus challenging MLLMs to faithfully comprehend and reason about multiple events over extended periods of time. To facilitate the study, we construct DeVE-QA -- a dataset featuring 78K questions about 26K events on 10.6K long videos. Our benchmarking shows that state-of-the-art MLLMs struggle on DeVE-QA. For improvement, we propose DeVi, a novel training-free MLLM approach that highlights a hierarchical captioning module, a temporal event memory module, and a self-consistency checking module to respectively detect, contextualize and memorize, and ground dense-events in long videos for question answering. Extensive experiments show that DeVi is superior at answering dense-event questions and grounding relevant video moments. Compared with existing MLLMs, it achieves a notable increase of 4.8% and 2.1% for G(round)QA accuracy on DeVE-QA and NExT-GQA, respectively. Data and code are available at https://github.com/QHUni/DeVE-QA.

cs.CV↗

arXiv2025

A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds

3D Gaussian Splatting (3DGS) is a powerful reconstruction technique, but it needs to be initialized from accurate camera poses and high-fidelity point clouds. Typically, the initialization is taken from Structure-from-Motion (SfM) algorithms; however, SfM is time-consuming and restricts the application of 3DGS in real-world scenarios and large-scale scene reconstruction. We introduce a constrained optimization method for simultaneous camera pose estimation and 3D reconstruction that does not require SfM support. Core to our approach is decomposing a camera pose into a sequence of camera-to-(device-)center and (device-)center-to-world optimizations. To facilitate, we propose two optimization constraints conditioned to the sensitivity of each parameter group and restricts each parameter's search space. In addition, as we learn the scene geometry directly from the noisy point clouds, we propose geometric constraints to improve the reconstruction quality. Experiments demonstrate that the proposed method significantly outperforms the existing (multi-modal) 3DGS baseline and methods supplemented by COLMAP on both our collected dataset and two public benchmarks.

cs.CV↗

arXiv2025

Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding

We introduce ProVideLLM, an end-to-end framework for real-time procedural video understanding. ProVideLLM integrates a multimodal cache configured to store two types of tokens - verbalized text tokens, which provide compressed textual summaries of long-term observations, and visual tokens, encoded with DETR-QFormer to capture fine-grained details from short-term observations. This design reduces token count by 22x over existing methods in representing one hour of long-term observations while effectively encoding fine-granularity of the present. By interleaving these tokens in our multimodal cache, ProVideLLM ensures sub-linear scaling of memory and compute with video length, enabling per-frame streaming inference at 10 FPS and streaming dialogue at 25 FPS, with a minimal 2GB GPU memory footprint. ProVideLLM also sets new state-of-the-art results on six procedural tasks across four datasets.

cs.CV↗

arXiv2025

Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation

Recent synthetic 3D human datasets for the face, body, and hands have pushed the limits on photorealism. Face recognition and body pose estimation have achieved state-of-the-art performance using synthetic training data alone, but for the hand, there is still a large synthetic-to-real gap. This paper presents the first systematic study of the synthetic-to-real gap of 3D hand pose estimation. We analyze the gap and identify key components such as the forearm, image frequency statistics, hand pose, and object occlusions. To facilitate our analysis, we propose a data synthesis pipeline to synthesize high-quality data. We demonstrate that synthetic hand data can achieve the same level of accuracy as real data when integrating our identified components, paving the path to use synthetic data alone for hand pose estimation. Code and data are available at: https://github.com/delaprada/HandSynthesis.git.

cs.CV↗

arXiv2025

Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentation

Temporal action segmentation in untrimmed procedural videos aims to densely label frames into action classes. These videos inherently exhibit long-tailed distributions, where actions vary widely in frequency and duration. In temporal action segmentation approaches, we identified a bi-level learning bias. This bias encompasses (1) a class-level bias, stemming from class imbalance favoring head classes, and (2) a transition-level bias arising from variations in transitions, prioritizing commonly observed transitions. As a remedy, we introduce a constrained optimization problem to alleviate both biases. We define learning states for action classes and their associated transitions and integrate them into the optimization process. We propose a novel cost-sensitive loss function formulated as a weighted cross-entropy loss, with weights adaptively adjusted based on the learning state of actions and their transitions. Experiments on three challenging temporal segmentation benchmarks and various frameworks demonstrate the effectiveness of our approach, resulting in significant improvements in both per-class frame-wise and segment-wise performance.

cs.CV↗