arXiv subjects

Ting Lei

Publications and source records attributed to Ting Lei.

At least 19 recordsLinked to original sources

arXiv2026

ReART: Reference-Guided Retrieval and Refinement for Emotion-Aware Art Generation

Emotion-aware artistic image generation requires a model to satisfy semantic content, artistic style, and target emotion simultaneously. The key challenge is that artistic captions conflate these axes into underspecified free-form text, making fine-grained visual attributes such as brushwork, composition, and tonal atmosphere difficult to ground concretely. We present ReART, a reference-guided retrieval and refinement framework. Our method decomposes test captions and each image annotation in the EmoArt database into structured visual fields, and performs field-wise retrieval over subject, layout, brush-line, and tone-mood dimensions to retrieve role-specific visual references that supply the perceptual detail text alone cannot convey; these references are used alongside a structured prompt for initial synthesis. For samples where any Attribute Alignment Score (AAS) axis falls below threshold, an AAS-driven refinement loop diagnoses failures, constructs constrained repair plans specifying elements to keep, errors to fix, and operations to avoid, routes references by correction purpose, and performs controlled editing under structural preservation constraints. Our system ranks 2nd in Track 1 of the AffectiveArt 2026 Grand Challenge, achieving a perfect AAS of 1.00 and an overall score of 0.78. Code is available at https://github.com/oceanflowlab/ReART.git.

cs.MM↗

arXiv2026

Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models

Multimodal large language models (MLLMs) combine linguistic reasoning with visual perception, yet their ability to perform visual spatial planning under explicit or previously unseen rule constraints remains underexplored. This setting requires models to jointly understand spatial layouts, interpret natural-language rules, and plan valid actions accordingly. To address this gap, we introduce RuleMaze, a controllable benchmark in which MLLMs must navigate mazes while obeying natural-language rules of varying complexity. RuleMaze isolates rule-compliant spatial planning by requiring accurate perception, rule interpretation, and constrained action planning. To enable scalable and systematic rule construction, we propose Language-Logic-Function Hybridization, which automatically generates natural-language rules and translates them into logical representations and executable validators, eliminating manual rule engineering. To improve rule following and generalization, we introduce Disentangled Multimodal Planning (DMP), which separates perception, execution, and rule verification through interpretable reasoning primitives. By disentangling these components, DMP facilitates systematic generalization to more complex and previously unseen rules, while providing transparent intermediate planning traces. Experiments demonstrate that DMP substantially improves rule compliance and planning success compared to end-to-end textual planning baselines. Overall, RuleMaze establishes a principled benchmark for studying grounded and interpretable rule-based spatial planning in MLLMs. Code is available at https://github.com/oceanflowlab/RuleMaze.

cs.AI↗

arXiv2026

Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild

Human-object interaction detection (HOID) has traditionally been formulated as a supervised detection problem over predefined interaction categories. While such paradigms achieve strong performance on closed-set benchmarks, they fundamentally entangle interaction understanding with dataset-specific supervision, limiting their ability to generalize to open-world and compositional scenarios. Recent HOI detectors attempt to leverage MLLMs through prompting strategies to transfer interaction-specific knowledge. However, such prompt-based approaches primarily focus on extracting discriminative representations from pretrained models, while underexploring their inherent multimodal reasoning capabilities. As a result, they struggle to provide informative contextual reasoning for ambiguous and open-world interaction scenarios. In this work, we present AgentHOI, a training-free, agentic framework that transfers the generalist multimodal reasoning capabilities of foundation models to HOI detection in the wild. Instead of learning interaction classifiers, AgentHOI modularly orchestrates complementary vision foundation modules to perform open-ended semantic reasoning and spatial grounding in a coordinated manner. To address the challenges of incomplete interaction discovery and ambiguous localization in complex scenes, we introduce two key mechanisms: (1) Context-aware Multi-round Reasoning, which progressively refines interaction hypotheses to ensure exhaustive and compositional HOI discovery, and (2) Multifaceted Interaction Localization, which enhances grounding precision by generating instance-specific descriptions that integrate semantic, spatial, and appearance cues. Extensive experiments demonstrate that AgentHOI achieves superior performance over state-of-the-art supervised and weakly supervised methods in real-world settings, despite requiring no HOID data for training.

cs.CV↗

arXiv2026

ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools

Integrating external tools into Large Foundation Models (LFMs) has emerged as a promising approach to enhance their problem-solving capabilities. While existing studies have demonstrated strong performance in tool-augmented Visual Question Answering (VQA), recent benchmarks reveal significant gaps in real-world tool-use proficiency, particularly in functionally diverse multimodal settings requiring multi-step reasoning. In this work, we introduce ToolVQA, a large-scale multimodal dataset comprising 23K instances, designed to bridge this gap. Unlike previous datasets that rely on synthetic scenarios and simplified queries, ToolVQA features real-world visual contexts and challenging implicit multi-step reasoning tasks, better aligning with real user interactions. To construct this dataset, we propose ToolEngine, a novel data generation pipeline that employs Depth-First Search (DFS) with a dynamic in-context example matching mechanism to simulate human-like tool-use reasoning. ToolVQA encompasses 10 multimodal tools across 7 diverse task domains, with an average inference length of 2.78 reasoning steps per instance. The fine-tuned 7B LFMs on ToolVQA not only achieve impressive performance on our test set but also surpass the large close-sourced model GPT-3.5-turbo on various out-of-distribution (OOD) datasets, demonstrating strong generalizability to real-world tool-use scenarios.

cs.AI↗

arXiv2025

TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring

Dynamic Scene Graph Generation (DSGG) aims to create a scene graph for each video frame by detecting objects and predicting their relationships. Weakly Supervised DSGG (WS-DSGG) reduces annotation workload by using an unlocalized scene graph from a single frame per video for training. Existing WS-DSGG methods depend on an off-the-shelf external object detector to generate pseudo labels for subsequent DSGG training. However, detectors trained on static, object-centric images struggle in dynamic, relation-aware scenarios required for DSGG, leading to inaccurate localization and low-confidence proposals. To address the challenges posed by external object detectors in WS-DSGG, we propose a Temporal-enhanced Relation-aware Knowledge Transferring (TRKT) method, which leverages knowledge to enhance detection in relation-aware dynamic scenarios. TRKT is built on two key components:(1)Relation-aware knowledge mining: we first employ object and relation class decoders that generate category-specific attention maps to highlight both object regions and interactive areas. Then we propose an Inter-frame Attention Augmentation strategy that exploits optical flow for neighboring frames to enhance the attention maps, making them motion-aware and robust to motion blur. This step yields relation- and motion-aware knowledge mining for WS-DSGG. (2) we introduce a Dual-stream Fusion Module that integrates category-specific attention maps into external detections to refine object localization and boost confidence scores for object proposals. Extensive experiments demonstrate that TRKT achieves state-of-the-art performance on Action Genome dataset. Our code is avaliable at https://github.com/XZPKU/TRKT.git.

cs.CV↗

arXiv2025

Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration

Open Vocabulary Human-Object Interaction (HOI) detection aims to detect interactions between humans and objects while generalizing to novel interaction classes beyond the training set. Current methods often rely on Vision and Language Models (VLMs) but face challenges due to suboptimal image encoders, as image-level pre-training does not align well with the fine-grained region-level interaction detection required for HOI. Additionally, effectively encoding textual descriptions of visual appearances remains difficult, limiting the model's ability to capture detailed HOI relationships. To address these issues, we propose INteraction-aware Prompting with Concept Calibration (INP-CC), an end-to-end open-vocabulary HOI detector that integrates interaction-aware prompts and concept calibration. Specifically, we propose an interaction-aware prompt generator that dynamically generates a compact set of prompts based on the input scene, enabling selective sharing among similar interactions. This approach directs the model's attention to key interaction patterns rather than generic image-level semantics, enhancing HOI detection. Furthermore, we refine HOI concept representations through language model-guided calibration, which helps distinguish diverse HOI concepts by investigating visual similarities across categories. A negative sampling strategy is also employed to improve inter-modal similarity modeling, enabling the model to better differentiate visually similar but semantically distinct actions. Extensive experimental results demonstrate that INP-CC significantly outperforms state-of-the-art models on the SWIG-HOI and HICO-DET datasets. Code is available at https://github.com/ltttpku/INP-CC.

cs.CV↗

arXiv2025

Physically interpretable diffractive optical networks for high-dimensional vortex mode sorting

Despite the significant progress achieved by diffractive optical networks in diverse computing tasks, such as mode multiplexing and demultiplexing, investigations into the physical meanings behind complex diffractive networks at the layer level have been quite limited. Here, for highdimensional vortex mode sorting tasks, we show how various physical transformation rules for each layer within trained diffractive networks can be revealed under properly defined input/output mode relations. An intriguing physical transformation division phenomenon, associated with the saturated sorting performance of the system, has been observed with an increasing number of masks. In addition, we have also demonstrated the use of physical interpretation for efficiently designing parameter-varying networks with high performance. These physically interpretable optical networks resolve the contradiction between rigorous physical theorems and operationally vague network structures, paving the way for designing and understanding systems for various mode conversion tasks, and inspiring further interpretation of diffractive networks in advanced tasks and other network structures.

physics.optics↗

arXiv2024

Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection

Zero-shot Human-Object Interaction (HOI) detection has emerged as a frontier topic due to its capability to detect HOIs beyond a predefined set of categories. This task entails not only identifying the interactiveness of human-object pairs and localizing them but also recognizing both seen and unseen interaction categories. In this paper, we introduce a novel framework for zero-shot HOI detection using Conditional Multi-Modal Prompts, namely CMMP. This approach enhances the generalization of large foundation models, such as CLIP, when fine-tuned for HOI detection. Unlike traditional prompt-learning methods, we propose learning decoupled vision and language prompts for interactiveness-aware visual feature extraction and generalizable interaction classification, respectively. Specifically, we integrate prior knowledge of different granularity into conditional vision prompts, including an input-conditioned instance prior and a global spatial pattern prior. The former encourages the image encoder to treat instances belonging to seen or potentially unseen HOI concepts equally while the latter provides representative plausible spatial configuration of the human and object under interaction. Besides, we employ language-aware prompt learning with a consistency constraint to preserve the knowledge of the large foundation model to enable better generalization in the text branch. Extensive experiments demonstrate the efficacy of our detector with conditional multi-modal prompts, outperforming previous state-of-the-art on unseen classes of various zero-shot settings. The code and models are available at \url{https://github.com/ltttpku/CMMP}.

cs.CV↗

arXiv2024

Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection

Open-vocabulary human-object interaction (HOI) detection, which is concerned with the problem of detecting novel HOIs guided by natural language, is crucial for understanding human-centric scenes. However, prior zero-shot HOI detectors often employ the same levels of feature maps to model HOIs with varying distances, leading to suboptimal performance in scenes containing human-object pairs with a wide range of distances. In addition, these detectors primarily rely on category names and overlook the rich contextual information that language can provide, which is essential for capturing open vocabulary concepts that are typically rare and not well-represented by category names alone. In this paper, we introduce a novel end-to-end open vocabulary HOI detection framework with conditional multi-level decoding and fine-grained semantic enhancement (CMD-SE), harnessing the potential of Visual-Language Models (VLMs). Specifically, we propose to model human-object pairs with different distances with different levels of feature maps by incorporating a soft constraint during the bipartite matching process. Furthermore, by leveraging large language models (LLMs) such as GPT models, we exploit their extensive world knowledge to generate descriptions of human body part states for various interactions. Then we integrate the generalizable and fine-grained semantics of human body parts to improve interaction recognition. Experimental results on two datasets, SWIG-HOI and HICO-DET, demonstrate that our proposed method achieves state-of-the-art results in open vocabulary HOI detection. The code and models are available at https://github.com/ltttpku/CMD-SE-release.

cs.CV↗

arXiv2023

Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory

Human Object Interaction (HOI) detection aims to localize and infer the relationships between a human and an object. Arguably, training supervised models for this task from scratch presents challenges due to the performance drop over rare classes and the high computational cost and time required to handle long-tailed distributions of HOIs in complex HOI scenes in realistic settings. This observation motivates us to design an HOI detector that can be trained even with long-tailed labeled data and can leverage existing knowledge from pre-trained models. Inspired by the powerful generalization ability of the large Vision-Language Models (VLM) on classification and retrieval tasks, we propose an efficient Adaptive HOI Detector with Concept-guided Memory (ADA-CM). ADA-CM has two operating modes. The first mode makes it tunable without learning new parameters in a training-free paradigm. Its second mode incorporates an instance-aware adapter mechanism that can further efficiently boost performance if updating a lightweight set of parameters can be afforded. Our proposed method achieves competitive results with state-of-the-art on the HICO-DET and V-COCO datasets with much less training time. Code can be found at https://github.com/ltttpku/ADA-CM.

cs.CV↗

arXiv2022

EgoTaskQA: Understanding Human Tasks in Egocentric Videos

Understanding human tasks through video observations is an essential capability of intelligent agents. The challenges of such capability lie in the difficulty of generating a detailed understanding of situated actions, their effects on object states (i.e., state changes), and their causal dependencies. These challenges are further aggravated by the natural parallelism from multi-tasking and partial observations in multi-agent collaboration. Most prior works leverage action localization or future prediction as an indirect metric for evaluating such task understanding from videos. To make a direct evaluation, we introduce the EgoTaskQA benchmark that provides a single home for the crucial dimensions of task understanding through question-answering on real-world egocentric videos. We meticulously design questions that target the understanding of (1) action dependencies and effects, (2) intents and goals, and (3) agents' beliefs about others. These questions are divided into four types, including descriptive (what status?), predictive (what will?), explanatory (what caused?), and counterfactual (what if?) to provide diagnostic analyses on spatial, temporal, and causal understandings of goal-oriented tasks. We evaluate state-of-the-art video reasoning models on our benchmark and show their significant gaps between humans in understanding complex goal-oriented egocentric videos. We hope this effort will drive the vision community to move onward with goal-oriented video understanding and reasoning.

cs.CV↗

arXiv2022

Team PKU-WICT-MIPL PIC Makeup Temporal Video Grounding Challenge 2022 Technical Report

In this technical report, we briefly introduce the solutions of our team `PKU-WICT-MIPL' for the PIC Makeup Temporal Video Grounding (MTVG) Challenge in ACM-MM 2022. Given an untrimmed makeup video and a step query, the MTVG aims to localize a temporal moment of the target makeup step in the video. To tackle this task, we propose a phrase relationship mining framework to exploit the temporal localization relationship relevant to the fine-grained phrase and the whole sentence. Besides, we propose to constrain the localization results of different step sentence queries to not overlap with each other through a dynamic programming algorithm. The experimental results demonstrate the effectiveness of our method. Our final submission ranked 2nd on the leaderboard, with only a 0.55\% gap from the first.

cs.CV↗

arXiv2020

Multiple-image encryption and hiding with an optical diffractive neural network

A cascaded phase-only mask architecture (or an optical diffractive neural network) can be employed for different optical information processing tasks such as pattern recognition, orbital angular momentum (OAM) mode conversion, image salience detection and image encryption. However, for optical encryption and watermarking applications, such a system usually cannot process multiple pairs of input images and output images simultaneously. In our proposed scheme, multiple input images can be simultaneously fed to an optical diffractive neural network (DNN) system and each corresponding output image will be displayed in a non-overlap sub-region in the output imaging plane. Each input image undergoes a different optical transform in an independent channel within the same system. The multiple cascaded phase masks in the system can be effectively optimized by a wavefront matching algorithm. Similar to recent optical pattern recognition and mode conversion works, the orthogonality property is employed to design a multiplexed DNN.

cs.CV↗

arXiv2020

Design of optimal illumination patterns in single-pixel imaging using image dictionaries

Single-pixel imaging (SPI) has a major drawback that many sequential illuminations are required for capturing one single image with long acquisition time. Basis illumination patterns such as Fourier patterns and Hadamard patterns can achieve much better imaging efficiency than random patterns. But the performance is still sub-optimal since the basis patterns are fixed and non-adaptive for varying object images. This Letter proposes a novel scheme for designing and optimizing the illumination patterns adaptively from an image dictionary by extracting the common image features using principal component analysis (PCA). Simulation and experimental results reveal that our proposed scheme outperforms conventional Fourier SPI in terms of imaging efficiency.

eess.IV↗

arXiv2020

Does deep learning always outperform simple linear regression in optical imaging?

Deep learning has been extensively applied in many optical imaging applications in recent years. Despite the success, the limitations and drawbacks of deep learning in optical imaging have been seldom investigated. In this work, we show that conventional linear-regression-based methods can outperform the previously proposed deep learning approaches for two black-box optical imaging problems in some extent. Deep learning demonstrates its weakness especially when the number of training samples is small. The advantages and disadvantages of linear-regression-based methods and deep learning are analyzed and compared. Since many optical systems are essentially linear, a deep learning network containing many nonlinearity functions sometimes may not be the most suitable option.

cs.CV↗

arXiv2019

Optical machine learning with incoherent light and a single-pixel detector

An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner. However, the system can only work under coherent light illumination and the precision requirement in practical experiments is quite high. This paper proposes an optical machine learning framework based on single-pixel imaging (MLSPI). The MLSPI system can perform the same linear pattern recognition task as DNN. Furthermore, it can work under incoherent lighting conditions, has lower experimental complexity and can be easily programmable.

cs.CV↗

arXiv2019

Visual cryptography in single-pixel imaging

Two novel visual cryptography (VC) schemes are proposed by combining VC with single-pixel imaging (SPI) for the first time. It is pointed out that the overlapping of visual key images in VC is similar to the superposition of pixel intensities by a single-pixel detector in SPI. In the first scheme, QR-code VC is designed by using opaque sheets instead of transparent sheets. The secret image can be recovered when identical illumination patterns are projected onto multiple visual key images and a single detector is used to record the total light intensities. In the second scheme, the secret image is shared by multiple illumination pattern sequences and it can be recovered when the visual key patterns are projected onto identical items. The application of VC can be extended to more diversified scenarios by our proposed schemes.

eess.IV↗

arXiv2019

A novel linear battery energy storage system (BESS) life loss calculation model for BESS-integrated wind farm in scheduled power tracking

Recently, rapid development of battery technology makes it feasible to integrate renewable generations with battery energy storage system (BESS). The consideration of BESS life loss for different BESS application scenarios is economic imperative. In this paper, a novel linear BESS life loss calculation model for BESS-integrated wind farm in scheduled power tracking is proposed. Firstly, based on the life cycle times-depth of discharge (DOD) relation-curve, the BESS life loss coefficient for unit throughput energy with different state of charge (SOC) can be determined from the life cycle times-DOD relation-curve fitting function directly. Secondly, as unidirectional variation of SOC in a single time step, the BESS life loss can be calculated through integration of the life loss coefficient-SOC relation function. A linear BESS life loss calculation model is established through self-optimal piecewise linearization of the primitive function of the life loss coefficient-SOC relation function. Thirdly, the proposed life loss calculation model is incorporated in the BESS-integrated wind farm scheduled power tracking optimization. Case studies demonstrate that with the proposed method, the BESS life loss item can be incorporated in the optimization model effectively, and the scheduled power tracking cost of the BESS-integrated wind farm can be determined and optimized more comprehensively.

eess.SP↗