arXiv subjects

Bingqing Zhang

Publications and source records attributed to Bingqing Zhang.

13 recordsLinked to original sources

arXiv2026

DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding

Text-guided Video Temporal Grounding (VTG) aims to localize the relevant segments in an untrimmed video based on text queries, yet collecting dense temporal annotations and training task-specific models remain costly and brittle under distribution shift. Recent training-free VTG approaches mitigate this issue by directly matching pretrained vision-language representations, but they still face two fundamental information bottlenecks: frame-wise visual encoding overlooks temporal dynamics, while fixed query embeddings cannot resolve query ambiguity. To address these issues, we propose DSE-VTG, a \underline{D}ual-\underline{S}ide \underline{E}nhancement framework that addresses both without any task-specific training. On the visual side, Multi-scale Similarity Fusion (MSF) combines frame- and clip-level similarities into a unified, temporally aware similarity profile. On the textual side, Query-level Test-Time Adaptation (Q-TTA) optimizes a lightweight additive offset to adapt the query embedding to the video at test time, without finetuning the backbone or calling external large language models. Extensive experiments on three standard and two OOD benchmarks show that DSE-VTG achieves state-of-the-art performance among training-free methods. On Charades-STA, it improves mIoU over the strongest prior training-free method by 5.61 points. Under distribution shift, DSE-VTG reaches 50.86 mIoU on Charades-CG Novel-Word, surpassing the strongest supervised baseline by 2.76 mIoU. Our code will be released upon acceptance.

cs.CV↗

arXiv2026

ReCoVR: Closing the Loop in Interactive Composed Video Retrieval

Composed video retrieval (CoVR) searches for target videos using a reference video and a modification text, but existing methods are restricted to a single interaction round and cannot support the progressive nature of real-world visual search. To bridge this gap, we first formalize interactive composed video retrieval, a multi-turn extension of CoVR, where users progressively refine their search intent through natural-language feedback across turns. Adapting existing interactive retrieval methods to this setting reveals two structural weaknesses: reliance on a single retrieval channel and an open-loop retrieval design that consumes user feedback but does not diagnose whether its own retrieval trajectory is drifting or stagnating. To address these limitations, we propose ReCoVR (Reflexive Composed Video Retrieval), a dual-pathway architecture built on reflexive perception, where the system treats its retrieval history as diagnostic evidence alongside user feedback. Specifically, an Intent Pathway routes heterogeneous feedback to complementary retrieval channels, while a Reflection Pathway performs trajectory-level reflection to monitor result evolution and correct retrieval errors across turns. Experiments on multiple benchmarks show that ReCoVR consistently outperforms interactive baselines, notably achieving 74.30% R@1 after just one interactive round on the WebVid-CoVR-Test dataset.

cs.IR↗

arXiv2026

Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts

Modern video-text retrieval (VTR) models excel on in-distribution benchmarks but are highly vulnerable to real-world query shifts, where the distribution of query data deviates from the training domain, leading to a sharp performance drop. Existing image-focused robustness solutions are inadequate to handle this vulnerability in video, as they fail to address the complex spatio-temporal dynamics inherent in these shifts. To systematically evaluate this vulnerability, we first introduce a comprehensive benchmark featuring 12 distinct types of video perturbations across five severity degrees. Analysis on this benchmark reveals that query shifts amplify the hubness phenomenon, where a few gallery items become dominant "hubs" that attract a disproportionate number of queries. To mitigate this, we then propose HAT-VTR (Hubness Alleviation for Test-time Video-Text Retrieval), as our baseline test-time adaptation framework designed to directly counteract hubness in VTR. It leverages two key components: a Hubness Suppression Memory to refine similarity scores, and multi-granular losses to enforce temporal feature consistency. Extensive experiments demonstrate that HAT-VTR substantially improves robustness, consistently outperforming prior methods across diverse query shift scenarios, and enhancing model reliability for real-world applications.

cs.IR↗

arXiv2025

The Size Evolution and the Size-Mass Relation of Lyman-Alpha Emitters across $3 \lesssim z < 7$ as Observed by JWST

Understanding the morphological structures of Lyman-alpha emitters (LAEs) is crucial for unveiling their formation pathways and the physical origins of Ly$α$ emission. However, the evolution of their sizes and structural scaling relations remains debated. In this study, we analyze a large sample of 876 spectroscopically confirmed LAEs at $3 \lesssim z < 7$, selected from the MUSE, VANDELS, and CANDELSz7 surveys in the GOODS-S, UDS, and COSMOS fields. Utilizing James Webb Space Telescope (JWST) NIRCam imaging data, we measure their rest-frame UV and optical V-band effective radii ($R_{\rm e}$) through two-dimensional Sérsic profile fitting. Our results show that these LAEs are generally compact, with a median $R_{\rm e,UV}$ of 0.50$^{+0.30}_{-0.24}$ kpc and a median $R_{\rm e,V}$ of 0.57$^{+0.33}_{-0.24}$ kpc. The size evolution follows $R_{\rm e,UV} \propto (1 + z)^{-0.91 \pm 0.10}$ and $R_{\rm e,V} \propto (1 + z)^{-0.93 \pm 0.18}$, respectively. Their UV and optical sizes are statistically comparable, indicating negligible UV-to-optical color gradients. For the first time, we establish the rest-frame optical size-mass relation for LAEs at $z>3$, finding slopes comparable to typical star-forming galaxies (SFGs), but with slightly smaller sizes at a given stellar mass. These results provide important clues for understanding structural evolution of LAEs in the early universe.

astro-ph.GA↗

arXiv2025

When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions

Existing Moment retrieval (MR) methods focus on Single-Moment Retrieval (SMR). However, one query can correspond to multiple relevant moments in real-world applications. This makes the existing datasets and methods insufficient for video temporal grounding. By revisiting the gap between current MR tasks and real-world applications, we introduce a high-quality datasets called QVHighlights Multi-Moment Dataset (QV-M$^2$), along with new evaluation metrics tailored for multi-moment retrieval (MMR). QV-M$^2$ consists of 2,212 annotations covering 6,384 video segments. Building on existing efforts in MMR, we propose a framework called FlashMMR. Specifically, we propose a Multi-moment Post-verification module to refine the moment boundaries. We introduce constrained temporal adjustment and subsequently leverage a verification module to re-evaluate the candidate segments. Through this sophisticated filtering pipeline, low-confidence proposals are pruned, and robust multi-moment alignment is achieved. We retrain and evaluate 6 existing MR methods on QV-M$^2$ and QVHighlights under both SMR and MMR settings. Results show that QV-M$^2$ serves as an effective benchmark for training and evaluating MMR models, while FlashMMR provides a strong baseline. Specifically, on QV-M$^2$, it achieves improvements over prior SOTA method by 3.00% on G-mAP, 2.70% on mAP@3+tgt, and 2.56% on mR@3. The proposed benchmark and method establish a foundation for advancing research in more realistic and challenging video temporal grounding scenarios. Code is released at https://github.com/Zhuo-Cao/QV-M2.

cs.CV↗

arXiv2025

Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization

Despite recent advances, Text-to-video retrieval (TVR) is still hindered by multiple inherent uncertainties, such as ambiguous textual queries, indistinct text-video mappings, and low-quality video frames. Although interactive systems have emerged to address these challenges by refining user intent through clarifying questions, current methods typically rely on heuristic or ad-hoc strategies without explicitly quantifying these uncertainties, limiting their effectiveness. Motivated by this gap, we propose UMIVR, an Uncertainty-Minimizing Interactive Text-to-Video Retrieval framework that explicitly quantifies three critical uncertainties-text ambiguity, mapping uncertainty, and frame uncertainty-via principled, training-free metrics: semantic entropy-based Text Ambiguity Score (TAS), Jensen-Shannon divergence-based Mapping Uncertainty Score (MUS), and a Temporal Quality-based Frame Sampler (TQFS). By adaptively generating targeted clarifying questions guided by these uncertainty measures, UMIVR iteratively refines user queries, significantly reducing retrieval ambiguity. Extensive experiments on multiple benchmarks validate UMIVR's effectiveness, achieving notable gains in Recall@1 (69.2\% after 10 interactive rounds) on the MSR-VTT-1k dataset, thereby establishing an uncertainty-minimizing foundation for interactive TVR.

cs.CV↗

arXiv2024

FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding

Text-guided Video Temporal Grounding (VTG) aims to localize relevant segments in untrimmed videos based on textual descriptions, encompassing two subtasks: Moment Retrieval (MR) and Highlight Detection (HD). Although previous typical methods have achieved commendable results, it is still challenging to retrieve short video moments. This is primarily due to the reliance on sparse and limited decoder queries, which significantly constrain the accuracy of predictions. Furthermore, suboptimal outcomes often arise because previous methods rank predictions based on isolated predictions, neglecting the broader video context. To tackle these issues, we introduce FlashVTG, a framework featuring a Temporal Feature Layering (TFL) module and an Adaptive Score Refinement (ASR) module. The TFL module replaces the traditional decoder structure to capture nuanced video content variations across multiple temporal scales, while the ASR module improves prediction ranking by integrating context from adjacent moments and multi-temporal-scale features. Extensive experiments demonstrate that FlashVTG achieves state-of-the-art performance on four widely adopted datasets in both MR and HD. Specifically, on the QVHighlights dataset, it boosts mAP by 5.8% for MR and 3.3% for HD. For short-moment retrieval, FlashVTG increases mAP to 125% of previous SOTA performance. All these improvements are made without adding training burdens, underscoring its effectiveness. Our code is available at https://github.com/Zhuo-Cao/FlashVTG.

cs.CV↗

arXiv2024

TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm

Text-Video Retrieval (TVR) methods typically match query-candidate pairs by aligning text and video features in coarse-grained, fine-grained, or combined (coarse-to-fine) manners. However, these frameworks predominantly employ a one(query)-to-one(candidate) alignment paradigm, which struggles to discern nuanced differences among candidates, leading to frequent mismatches. Inspired by Comparative Judgement in human cognitive science, where decisions are made by directly comparing items rather than evaluating them independently, we propose TokenBinder. This innovative two-stage TVR framework introduces a novel one-to-many coarse-to-fine alignment paradigm, imitating the human cognitive process of identifying specific items within a large collection. Our method employs a Focused-view Fusion Network with a sophisticated cross-attention mechanism, dynamically aligning and comparing features across multiple videos to capture finer nuances and contextual variations. Extensive experiments on six benchmark datasets confirm that TokenBinder substantially outperforms existing state-of-the-art methods. These results demonstrate its robustness and the effectiveness of its fine-grained alignment in bridging intra- and inter-modality information gaps in TVR tasks.

cs.CV↗

arXiv2023

Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection

Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased computational complexity. In this work, we propose an image-level Object Detection Difficulty (ODD) metric to quantify the difficulty of detecting objects in a given image. The derived ODD scores can be used in the VOD process to mitigate over-aggregation. Specifically, we train an ODD predictor as an auxiliary head of a still-image object detector to compute the ODD score for each image based on the discrepancies between detection results and ground-truth bounding boxes. The ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD Scheduler to eliminate the aggregation of frames that are easy to detect, thus accelerating the VOD process. Comprehensive experiments demonstrate that, when utilized for selecting global reference frames, ODD-VOD consistently enhances the accuracy of Global-frame-based VOD models. When employed for acceleration, ODD-VOD consistently improves the frames per second (FPS) by an average of 73.3% across 8 different VOD models without sacrificing accuracy. When combined, ODD-VOD attains state-of-the-art performance when competing with many VOD methods in both accuracy and speed. Our work represents a significant advancement towards making VOD more practical for real-world applications.

cs.CV↗

arXiv2022

InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee

After a survey for person-tracking system-induced privacy concerns, we propose a black-box adversarial attack method on state-of-the-art human detection models called InvisibiliTee. The method learns printable adversarial patterns for T-shirts that cloak wearers in the physical world in front of person-tracking systems. We design an angle-agnostic learning scheme which utilizes segmentation of the fashion dataset and a geometric warping process so the adversarial patterns generated are effective in fooling person detectors from all camera angles and for unseen black-box detection models. Empirical results in both digital and physical environments show that with the InvisibiliTee on, person-tracking systems' ability to detect the wearer drops significantly.

cs.CV↗

arXiv2022

STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval

We propose a video feature representation learning framework called STAR-GNN, which applies a pluggable graph neural network component on a multi-scale lattice feature graph. The essence of STAR-GNN is to exploit both the temporal dynamics and spatial contents as well as visual connections between regions at different scales in the frames. It models a video with a lattice feature graph in which the nodes represent regions of different granularity, with weighted edges that represent the spatial and temporal links. The contextual nodes are aggregated simultaneously by graph neural networks with parameters trained with retrieval triplet loss. In the experiments, we show that STAR-GNN effectively implements a dynamic attention mechanism on video frame sequences, resulting in the emphasis for dynamic and semantically rich content in the video, and is robust to noise and redundancies. Empirical results show that STAR-GNN achieves state-of-the-art performance for Content-Based Video Retrieval.

cs.CV↗

arXiv2022

Optical Observations of the Nearby Type Ia Supernova 2021hpr

We present the optical photometric and spectroscopic observations of the nearby Type Ia supernova (SN) 2021hpr. The observations covered the phase of $-$14.37 to +63.68 days relative to its maximum luminosity in the $B$ band. The evolution of multiband light/color curves of SN 2021hpr is similar to that of normal Type Ia supernovae (SNe Ia) with the exception of some phases, especially a plateau phase that appeared in the $V-R$ color curve before peak luminosity, which resembles that of SN 2017cbv. The first spectrum we observed at t $\sim -$14.4 days shows a higher velocity for the Si II $λ$6355 feature ($\sim$ 21,000 km s$^{-1}$) than that of other normal Velocity (NV) SNe Ia at the same phase. Based on the Si II $λ$6355 velocity of $\sim$ 12,420 km s$^{-1}$ around the maximum light, we deduce that SN 2021hpr is a transitional object between high velocity (HV) and NV SNe Ia. Meanwhile, the Si II $λ$6355 feature shows a high velocity gradient (HVG) of about 800 km s$^{-1}$ day$^{-1}$ from roughly $-$14.37 to $-$4.31 days relative to the $B$-band maximum, which indicates that SN 2021hpr can also be classified as an HVG SN Ia. The evolution of SN 2021hpr is similar to that of SN 2011fe. Including SN 2021hpr, there have been six supernovae observed in the host galaxy NGC 3147, and the supernovae explosion rate in the last 50 yr is slightly higher for SNe Ia, while lower for SNe Ibc and SNe II it is lower than expected rate from the radio data. Inspecting the spectra, we find that SN 2021hpr has a metal-rich (12 + log(O/H) $\approx$ 8.648) circumstellar environment, where HV SNe tend to reside. Based on the decline rate of SN 2021hpr in the $B$ band, we determine the distance modulus of the host galaxy NGC 3147 using the Phillips relation to be 33.46 $\pm$ 0.21 mag, which is close to that found by previous works.

astro-ph.HE↗

arXiv2020

OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets

Human Trajectory Prediction (HTP) has gained much momentum in the last years and many solutions have been proposed to solve it. Proper benchmarking being a key issue for comparing methods, this paper addresses the question of evaluating how complex is a given dataset with respect to the prediction problem. For assessing a dataset complexity, we define a series of indicators around three concepts: Trajectory predictability; Trajectory regularity; Context complexity. We compare the most common datasets used in HTP in the light of these indicators and discuss what this may imply on benchmarking of HTP algorithms. Our source code is released on Github.

cs.CV↗