arXiv subjects

Jen-Jee Chen

Publications and source records attributed to Jen-Jee Chen.

9 recordsLinked to original sources

arXiv2026

AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models

This study investigates the challenge of ambiguity faced by Vision-Language Models (VLMs) in understanding spatial semantics. Spatial cognition, shaped by cognitive psychology, spatial science, and cultural context, often assigns directionality to objects. However, natural language descriptions of spatial relations frequently omit explicit reference frames, leading to semantic ambiguity and potentially serious errors for embodied AI robots. Existing VLMs, due to insufficient training on reference frames and object orientations, often produce inconsistent responses. To address this issue, we construct a new dataset, AlloEgo-View, comprising (image, query, view-specific answer) triplets that capture key object relations from both allocentric and egocentric perspectives. The view-specific descriptions follow a structured spatial representation that annotate detailed scene descriptions, reference and target objects, their orientations, reference frames, and view types. Building on AlloEgo-View, we develop AlloEgo-VLM, a framework to disambiguate allocentric and egocentric reference frames, even under ambiguous queries, and to be easily integrated into existing VLMs via supervised fine-tuning. Furthermore, we deploy our framework onto an embodied robotic platform within NVIDIA Isaac Sim to validate its real-world feasibility in open-ended object searching tasks. Experiments highlight the limitations of current VLMs in handling view-specific queries and demonstrate the strong disambiguation ability of AlloEgo-VLM.

cs.CV↗

arXiv2026

DynoDINO: Harnessing Dynamic Latent Information from DINO Features for Multi-Phase Medical Image Segmentation

Multi-phase Contrast-Enhanced Computed Tomography (CECT) plays a central role in the diagnosis and characterization of focal lesions by capturing temporal enhancement patterns across multiple acquisition phases. Accurate lesion segmentation from such data remains challenging because clinically relevant contrast kinetics are distributed across phases, while anatomical inconsistencies, respiratory motion, and incomplete acquisitions often lead to inter-phase misalignment and interrupted temporal information. Conventional segmentation frameworks typically process each phase independently or rely on simple fusion strategies, limiting their temporal reasoning capability. To address these challenges, we propose DynoDINO, a unified framework tailored to address the core challenges of multi-phase medical image segmentation. DynoDINO first performs slice-level alignment to establish inter-phase anatomical correspondence and then employs a Multi-phase Fusion Model to jointly enhance temporal correlations across phases. Our fusion model incorporates a Mix-attention (MA) mechanism for efficient multi-phase feature calibration and an Adaptive Gating Mechanism with difference-based residual learning to selectively preserve diagnostically relevant contrast variations while suppressing artifacts caused by residual misalignment. In addition, the adaptive gating mechanism improves training stability by preventing feature degradation caused by unguided subtraction operations. Experiments on three large-scale datasets, including LiTS, PLC-CECT, and WAW-TACE, demonstrate that DynoDINO consistently improves boundary delineation and structural fidelity under standard, shifted, and missing-phase conditions.

cs.CV↗

arXiv2026

Learning Displacement-Aware WiFi Representations for Weakly Supervised Relative Localization

WiFi fingerprint-based indoor localization has been widely studied, but most existing approaches focus on absolute positioning and rely on dense coordinate annotations, which are costly to obtain at scale. In this paper, we study a fundamentally different problem: relative localization, where the goal is to directly estimate the displacement between two WiFi fingerprint traces without predicting their absolute positions. To reduce annotation overhead, we adopt weak supervision in the form of stepwise motion vectors obtained from inertial sensing. We propose Intersection Pathway (IP), a cross-modal learning framework that aligns fingerprint traces (f-traces) and displacement traces (d-traces) in a shared latent space. The key idea is to enforce an additive structure in the latent space, such that latent addition and subtraction correspond to physical motion composition, enabling direct relative-displacement inference. Experiments on a synthesized dataset derived from real measurements demonstrate that the proposed method learns displacement-aware WiFi representations and achieves accurate relative localization across varying displacement ranges. Furthermore, the learned model can be extended to few-shot absolute localization with sparse anchors.

eess.SP↗

arXiv2026

WiFi2Cap: Semantic Action Captioning from Wi-Fi CSI via Limb-Level Semantic Alignment

Privacy-preserving semantic understanding of human activities is important for indoor sensing, yet existing Wi-Fi CSI-based systems mainly focus on pose estimation or predefined action classification rather than fine-grained language generation. Mapping CSI to natural-language descriptions remains challenging because of the semantic gap between wireless signals and language and direction-sensitive ambiguities such as left/right limb confusion. We propose WiFi2Cap, a three-stage framework for generating action captions directly from Wi-Fi CSI. A vision-language teacher learns transferable supervision from synchronized video-text pairs, and a CSI student is aligned to the teacher's visual space and text embeddings. To improve direction-sensitive captioning, we introduce a Mirror-Consistency Loss that reduces mirrored-action and left-right ambiguities during cross-modal alignment. A prefix-tuned language model then generates action descriptions from CSI embeddings. We also introduce the WiFi2Cap Dataset, a synchronized CSI-RGB-sentence benchmark for semantic captioning from Wi-Fi signals. Experimental results show that WiFi2Cap consistently outperforms baseline methods on BLEU-4, METEOR, ROUGE-L, CIDEr, and SPICE, demonstrating effective privacy-friendly semantic sensing.

cs.CV↗

arXiv2026

Multi-User Multi-Key Image Steganography with Key Isolation

Steganography conceals secret information within innocuous carriers while preserving visual fidelity and enabling reliable recovery. Recent unified networks operate normally under untriggered conditions but switch to hidden steganographic tasks when triggered. PUSNet follows this paradigm by performing image purification during normal operation and steganographic embedding when activated. However, it supports only a single user with one key pair, limiting its applicability in multi-user settings. We propose PUSNet-MK, a multi-key extension that enforces strict key isolation via a mismatched-key isolation loss, effectively preventing cross-key decoding when a wrong key is applied. This design preserves the intended steganographic behavior while addressing a critical security limitation of PUSNet. Extensive experiments demonstrate that PUSNet-MK produces high-quality stego images and accurate secret recovery, while preventing unintended information leakage.

cs.CR↗

arXiv2025

DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs

Large Language Models (LLMs) have recently been extended to the video domain, enabling sophisticated video-language understanding. However, existing Video LLMs often exhibit limitations in fine-grained temporal reasoning, restricting their ability to precisely attribute responses to specific video moments, especially under constrained supervision. We introduce DaMO, a data-efficient Video LLM explicitly designed for accurate temporal reasoning and multimodal understanding. At its core, the proposed Temporal-aware Fuseformer employs a hierarchical dual-stream architecture that progressively captures temporal dynamics within each modality and effectively fuses complementary visual and audio information. To further enhance computational efficiency, DaMO integrates a global residual that reduces spatial redundancy while preserving essential semantic details. We train DaMO via a structured four-stage progressive training paradigm, incrementally equipping the model with multimodal alignment, semantic grounding, and temporal reasoning capabilities. This work also contributes multiple datasets augmented from existing ones with LLM-generated temporally grounded QA pairs for tasks requiring temporal supervision. Comprehensive experiments on temporal grounding and video QA benchmarks demonstrate that DaMO consistently surpasses prior methods, particularly in tasks demanding precise temporal alignment and reasoning. Our work establishes a promising direction for data-efficient video-language modeling.

cs.CV↗

arXiv2024

Resolving Positional Ambiguity in Dialogues by Vision-Language Models for Robot Navigation

We consider an autonomous navigation robot that can accept human commands through natural language to provide services in an indoor environment. These natural language commands may include time, position, object, and action components. However, we observe that the positional components within such commands usually refer to objects in the environment that may contain different levels of positional ambiguity. For example, the command "Go to the chair!" may be ambiguous when there are multiple chairs of the same type in a room. In order to disambiguate these commands, we employ a large language model and a large vision-language model to conduct multiple turns of conversations with the user. We propose a two-level approach that utilizes a vision-language model to map the meanings in natural language to a unique object ID in images and then performs another mapping from the unique object ID to a 3D depth map, thereby allowing the robot to navigate from its current position to the target position. To the best of our knowledge, this is the first work linking foundation models to the positional ambiguity issue.

cs.RO↗

arXiv2024

Learning-Based WiFi Fingerprint Inpainting via Generative Adversarial Networks

WiFi-based indoor positioning has been extensively studied. A fundamental issue in such solutions is the collection of WiFi fingerprints. However, due to real-world constraints, collecting complete fingerprints at all intended locations is sometimes prohibited. This work considers the WiFi fingerprint inpainting problem. This problem differs from typical image/video inpainting problems in several aspects. Unlike RGB images, WiFi field maps come in any shape, and signal data may follow certain distributions. Therefore, it is difficult to forcefully fit them into a fixed-dimensional matrix, as done with processing images in RGB format. As soon as a map is changed, it also becomes difficult to adapt it to the same model due to scale issues. Furthermore, such models are significantly constrained in situations requiring outward inpainting. Fortunately, the spatial relationships of WiFi signals and the rich information provided among channels offer ample opportunities for this generative model to accomplish inpainting. Therefore, we designed this model to not only retain the characteristic of regression models in generating fingerprints of arbitrary shapes but also to accommodate the observational outcomes from densely deployed APs. This work makes two major contributions. Firstly, we delineate the distinctions between this problem and image inpainting, highlighting potential avenues for research. Secondly, we introduce novel generative inpainting models aimed at capturing both inter-AP and intra-AP correlations while preserving latent information. Additionally, we incorporate a specially designed adversarial discriminator to enhance the quality of inpainting outcomes.

eess.SP↗

arXiv2023

Privacy-Preserving Video Conferencing via Thermal-Generative Images

Due to the COVID-19 epidemic, video conferencing has evolved as a new paradigm of communication and teamwork. However, private and personal information can be easily leaked through cameras during video conferencing. This includes leakage of a person's appearance as well as the contents in the background. This paper proposes a novel way of using online low-resolution thermal images as conditions to guide the synthesis of RGB images, bringing a promising solution for real-time video conferencing when privacy leakage is a concern. SPADE-SR (Spatially-Adaptive De-normalization with Self Resampling), a variant of SPADE, is adopted to incorporate the spatial property of a thermal heatmap and the non-thermal property of a normal, privacy-free pre-recorded RGB image provided in a form of latent code. We create a PAIR-LRT-Human (LRT = Low-Resolution Thermal) dataset to validate our claims. The result enables a convenient way of video conferencing where users no longer need to groom themselves and tidy up backgrounds for a short meeting. Additionally, it allows a user to switch to a different appearance and background during a conference.

cs.CR↗