arXiv subjects

Taotao Jing

Publications and source records attributed to Taotao Jing.

14 recordsLinked to original sources

arXiv2026

Conditional Multi-Event Temporal Grounding in Long-Form Video

Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing every event that satisfies compositional temporal and spatial conditions. Existing benchmarks fall short: they localize only a single moment per query, count without temporal conditions, or treat grounding and counting as disjoint tasks. We introduce CoMET-Bench for Conditional Multi-Event Temporal Grounding in long-form video, comprising 2789 queries over 600 videos averaging 33.8 minutes across five real-world domains, with each query composed from 4 temporal conditions, 3 spatial conditions, and a dedicated negative-query subset. We further propose a unified evaluation protocol jointly measuring counting, grounding, and negative-query recognition, including a new Rejection-F1 metric that prevents trivial gaming by lazy "always-empty" models. Benchmarking a broad suite of MLLMs, agent-based, and grounding-specialized methods reveals that existing approaches remain far from solving this task. Building on these findings, we propose CoMET-Agent, a training-free agentic framework that reformulates the task as structured search-and-aggregate, improving F1@0.5 by 6.1% over GPT-5 purely through structural reasoning. Failure analysis further surfaces three open directions: fine-grained entity tracking, position-uniform retrieval, and causal event pairing.

cs.CV↗

arXiv2026

Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference

Dual-system Vision-Language-Action (VLA) models achieve state-of-the-art robotic manipulation but are bottlenecked by the VLM backbone, which must execute at every control step while producing temporally redundant features. We propose Latent Bridge, a lightweight model that predicts VLM output deltas between timesteps, enabling the action head to operate on predicted outputs while the expensive VLM backbone is called only periodically. We instantiate Latent Bridge on two architecturally distinct VLAs: GR00T-N1.6 (feature-space bridge) and {\pi}0.5 (KV-cache bridge), demonstrating that the approach generalizes across VLA designs. Our task-agnostic DAgger training pipeline transfers across benchmarks without modification. Across four LIBERO suites, 24 RoboCasa kitchen tasks, and the ALOHA sim transfer-cube task, Latent Bridge achieves 95-100% performance retention while reducing VLM calls by 50-75%, yielding 1.65-1.73x net per-episode speedup.

cs.RO↗

arXiv2026

Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge

The IEEE Low-Power Computer Vision Challenge (LPCVC) aims to promote the development of efficient vision models for edge devices, balancing accuracy with constraints such as latency, memory capacity, and energy use. The 2025 challenge featured three tracks: (1) Image classification under various lighting conditions and styles, (2) Open-Vocabulary Segmentation with Text Prompt, and (3) Monocular Depth Estimation. This paper presents the design of LPCVC 2025, including its competition structure and evaluation framework, which integrates the Qualcomm AI Hub for consistent and reproducible benchmarking. The paper also introduces the top-performing solutions from each track and outlines key trends and observations. The paper concludes with suggestions for future computer vision competitions.

cs.CV↗

arXiv2026

ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance

Despite decades of work, surveillance still struggles in searching and reasoning about specific targets across long, multi-camera videos. Existing methods - tracking, retrieval, and video LLMs require heavy manual filtering, capture only shallow attributes, and fail at temporal understanding. Prior benchmarks are also limited to basic retrieval and question answering, without addressing real world challenges that often involve multimodal queries and temporal grounding (e.g., "When did this person join the fight?" with the person's image). To address this gap, we introduce ForeSeaQA, a new benchmark specifically designed for video QA with image-and-text queries and timestamped annotations of key events. The dataset consists of long-horizon surveillance footage paired with diverse multimodal questions, enabling systematic evaluation of retrieval, temporal grounding, and multimodal reasoning in realistic forensic conditions. Not limited to this benchmark, we propose ForeSea, an AI forensic search system with a 3-stage, plug-and-play pipeline. (1) A tracking module filters irrelevant footage; (2) a multimodal embedding module indexes the remaining clips; and (3) during inference, the system retrieves top-K candidate clips for a video LLM to answer queries and localize events. On ForeSeaQA benchmark, ForeSea improves accuracy by 3.1 points and temporal IoU by 10.1 points over prior retrieval-augmented baselines. To our knowledge, ForeSeaQA is the first benchmark to support complex multimodal queries with precise temporal grounding, and ForeSea is the first VideoRAG system built to excel in this setting.

cs.CV↗

arXiv2026

DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation

Open-vocabulary semantic segmentation aims to assign labels to every pixel in an image based on text labels. Existing approaches typically utilize vision-language models (VLMs), such as CLIP, for dense prediction. However, VLMs, pre-trained on image-text pairs, are biased toward salient, object-centric regions and exhibit two critical limitations when adapted to segmentation: (i) Foreground Bias, which tends to ignore background regions, and (ii) Limited Spatial Localization, resulting in blurred object boundaries. To address these limitations, we introduce DiSa, a novel saliency-aware foreground-background disentangled framework. By explicitly incorporating saliency cues in our designed Saliency-aware Disentanglement Module (SDM), DiSa separately models foreground and background ensemble features in a divide-and-conquer manner. Additionally, we propose a Hierarchical Refinement Module (HRM) that leverages pixel-wise spatial contexts and enables channel-wise feature refinement through multi-level updates. Extensive experiments on six benchmarks demonstrate that DiSa consistently outperforms state-of-the-art methods.

cs.CV↗

arXiv2025

VLMs Guided Interpretable Decision Making for Autonomous Driving

Recent advancements in autonomous driving (AD) have explored the use of vision-language models (VLMs) within visual question answering (VQA) frameworks for direct driving decision-making. However, these approaches often depend on handcrafted prompts and suffer from inconsistent performance, limiting their robustness and generalization in real-world scenarios. In this work, we evaluate state-of-the-art open-source VLMs on high-level decision-making tasks using ego-view visual inputs and identify critical limitations in their ability to deliver reliable, context-aware decisions. Motivated by these observations, we propose a new approach that shifts the role of VLMs from direct decision generators to semantic enhancers. Specifically, we leverage their strong general scene understanding to enrich existing vision-based benchmarks with structured, linguistically rich scene descriptions. Building on this enriched representation, we introduce a multi-modal interactive architecture that fuses visual and linguistic features for more accurate decision-making and interpretable textual explanations. Furthermore, we design a post-hoc refinement module that utilizes VLMs to enhance prediction reliability. Extensive experiments on two autonomous driving benchmarks demonstrate that our approach achieves state-of-the-art performance, offering a promising direction for integrating VLMs into reliable and interpretable AD systems.

cs.CV↗

arXiv2023

iBARLE: imBalance-Aware Room Layout Estimation

Room layout estimation predicts layouts from a single panorama. It requires datasets with large-scale and diverse room shapes to train the models. However, there are significant imbalances in real-world datasets including the dimensions of layout complexity, camera locations, and variation in scene appearance. These issues considerably influence the model training performance. In this work, we propose the imBalance-Aware Room Layout Estimation (iBARLE) framework to address these issues. iBARLE consists of (1) Appearance Variation Generation (AVG) module, which promotes visual appearance domain generalization, (2) Complex Structure Mix-up (CSMix) module, which enhances generalizability w.r.t. room structure, and (3) a gradient-based layout objective function, which allows more effective accounting for occlusions in complex layouts. All modules are jointly trained and help each other to achieve the best performance. Experiments and ablation studies based on ZInD~\cite{cruz2021zillow} dataset illustrate that iBARLE has state-of-the-art performance compared with other layout estimation baselines.

cs.CV↗

arXiv2021

PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions

Accurately modeling pedestrian intention and understanding driver decision-making processes are critical for the development of safe and socially aware autonomous driving systems. We introduce PSI, a benchmark dataset that captures the dynamic evolution of pedestrian crossing intentions from the driver's perspective, enriched with human textual explanations that reflect the reasoning behind intention estimation and driving decision making. These annotations offer a unique foundation for developing and benchmarking models that combine predictive performance with interpretable and human-aligned reasoning. PSI supports standardized tasks and evaluation protocols across multiple dimensions, including pedestrian intention prediction, driver decision modeling, reasoning generation, and trajectory forecasting and more. By enabling causal and interpretable evaluation, PSI advances research toward autonomous systems that can reason, act, and explain in alignment with human cognitive processes.

cs.CV↗

arXiv2021

Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation

Domain adaptation (DA) becomes an up-and-coming technique to address the insufficient or no annotation issue by exploiting external source knowledge. Existing DA algorithms mainly focus on practical knowledge transfer through domain alignment. Unfortunately, they ignore the fairness issue when the auxiliary source is extremely imbalanced across different categories, which results in severe under-presented knowledge adaptation of minority source set. To this end, we propose a Towards Fair Knowledge Transfer (TFKT) framework to handle the fairness challenge in imbalanced cross-domain learning. Specifically, a novel cross-domain mixup generation is exploited to augment the minority source set with target information to enhance fairness. Moreover, dual distinct classifiers and cross-domain prototype alignment are developed to seek a more robust classifier boundary and mitigate the domain shift. Such three strategies are formulated into a unified framework to address the fairness issue and domain shift challenge. Extensive experiments over two popular benchmarks have verified the effectiveness of our proposed model by comparing to existing state-of-the-art DA models, and especially our model significantly improves over 20% on two benchmarks in terms of the overall accuracy.

cs.CV↗

arXiv2021

Towards Novel Target Discovery Through Open-Set Domain Adaptation

Open-set domain adaptation (OSDA) considers that the target domain contains samples from novel categories unobserved in external source domain. Unfortunately, existing OSDA methods always ignore the demand for the information of unseen categories and simply recognize them as "unknown" set without further explanation. This motivates us to understand the unknown categories more specifically by exploring the underlying structures and recovering their interpretable semantic attributes. In this paper, we propose a novel framework to accurately identify the seen categories in target domain, and effectively recover the semantic attributes for unseen categories. Specifically, structure preserving partial alignment is developed to recognize the seen categories through domain-invariant feature learning. Attribute propagation over visual graph is designed to smoothly transit attributes from seen to unseen categories via visual-semantic mapping. Moreover, two new cross-main benchmarks are constructed to evaluate the proposed framework in the novel and practical challenge. Experimental results on open-set recognition and semantic recovery demonstrate the superiority of the proposed method over other compared baselines.

cs.CV↗

arXiv2020

Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation

Partial domain adaptation (PDA) attracts appealing attention as it deals with a realistic and challenging problem when the source domain label space substitutes the target domain. Most conventional domain adaptation (DA) efforts concentrate on learning domain-invariant features to mitigate the distribution disparity across domains. However, it is crucial to alleviate the negative influence caused by the irrelevant source domain categories explicitly for PDA. In this work, we propose an Adaptively-Accumulated Knowledge Transfer framework (A$^2$KT) to align the relevant categories across two domains for effective domain adaptation. Specifically, an adaptively-accumulated mechanism is explored to gradually filter out the most confident target samples and their corresponding source categories, promoting positive transfer with more knowledge across two domains. Moreover, a dual distinct classifier architecture consisting of a prototype classifier and a multilayer perceptron classifier is built to capture intrinsic data distribution knowledge across domains from various perspectives. By maximizing the inter-class center-wise discrepancy and minimizing the intra-class sample-wise compactness, the proposed model is able to obtain more domain-invariant and task-specific discriminative representations of the shared categories data. Comprehensive experiments on several partial domain adaptation benchmarks demonstrate the effectiveness of our proposed model, compared with the state-of-the-art PDA methods.

cs.CV↗

arXiv2020

Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation

Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. Conventional UDA concentrates on extracting domain-invariant features through deep adversarial networks. However, most of them seek to match the different domain feature distributions, without considering the task-specific decision boundaries across various classes. In this paper, we propose a novel Adversarial Dual Distinct Classifiers Network (AD$^2$CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries. To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment. Moreover, we naturally design two different structure classifiers to identify the unlabeled target samples over the supervision of the labeled source domain data. Such dual distinct classifiers with various architectures can capture diverse knowledge of the target data structure from different perspectives. Extensive experimental results on several cross-domain visual benchmarks prove the model's effectiveness by comparing it with other state-of-the-art UDA.

cs.CV↗

arXiv2020

Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation

Partial domain adaptation aims to adapt knowledge from a larger and more diverse source domain to a smaller target domain with less number of classes, which has attracted appealing attention. Recent practice on domain adaptation manages to extract effective features by incorporating the pseudo labels for the target domain to better fight off the cross-domain distribution divergences. However, it is essential to align target data with only a small set of source data. In this paper, we develop a novel Discriminative Cross-Domain Feature Learning (DCDF) framework to iteratively optimize target labels with a cross-domain graph in a weighted scheme. Specifically, a weighted cross-domain center loss and weighted cross-domain graph propagation are proposed to couple unlabeled target data to related source samples for discriminative cross-domain feature learning, where irrelevant source centers will be ignored, to alleviate the marginal and conditional disparities simultaneously. Experimental evaluations on several popular benchmarks demonstrate the effectiveness of our proposed approach on facilitating the recognition for the unlabeled target domain, through comparing it to the state-of-the-art partial domain adaptation approaches.

cs.CV↗

arXiv2020

EV-Action: Electromyography-Vision Multi-Modal Action Dataset

Multi-modal human action analysis is a critical and attractive research topic. However, the majority of the existing datasets only provide visual modalities (i.e., RGB, depth and skeleton). To make up this, we introduce a new, large-scale EV-Action dataset in this work, which consists of RGB, depth, electromyography (EMG), and two skeleton modalities. Compared with the conventional datasets, EV-Action dataset has two major improvements: (1) we deploy a motion capturing system to obtain high quality skeleton modality, which provides more comprehensive motion information including skeleton, trajectory, acceleration with higher accuracy, sampling frequency, and more skeleton markers. (2) we introduce an EMG modality which is usually used as an effective indicator in the biomechanics area, also it has yet to be well explored in motion related research. To the best of our knowledge, this is the first action dataset with EMG modality. The details of EV-Action dataset are clarified, meanwhile, a simple yet effective framework for EMG-based action recognition is proposed. Moreover, state-of-the-art baselines are applied to evaluate the effectiveness of all the modalities. The obtained result clearly shows the validity of EMG modality in human action analysis tasks. We hope this dataset can make significant contributions to human motion analysis, computer vision, machine learning, biomechanics, and other interdisciplinary fields.

cs.CV↗