论文检索

Surabhi Gupta, Dinesh Prabhu Muthumariappan, Biplab Das, Anoop Kolar Rajagopal, Kiran Nanjunda Iyer, Donghwan Seo

Eye images captured from wearable devices such as head-mounted displays (HMDs) contain identifiable biometric cues, posing significant challenges for safe data sharing. Existing eye anonymization techniques often degrade downstream performance, particularly gaze estimation while still retaining iris-recognizable features. Although these methods aim to anonymize the iris, they introduce noticeable visual artifacts that reduce image fidelity. To address these limitations, we propose PrivateEyes, a privacy-preserving framework that synthesizes anonymized yet gaze-consistent eye images. Our approach employs a three-stage pipeline: (1) a deep segmentation network that isolates semantic eye regions and provides structural control signals for synthesis, (2) a pose estimation network (PEN) trained on anatomically accurate synthetic eye renders to infer precise eye pose, and (3) a conditional diffusion model that reconstructs realistic, anonymized eye images conditioned on segmentation and pose. Extensive experiments across multiple benchmark datasets show that PrivateEyes achieves superior gaze-estimation accuracy compared to state-of-the-art anonymization baselines, improving performance by over 10% while reducing iris-recognition accuracy by ~50%. Our method also produces higher-fidelity images compared to other existing approaches. By enabling task-preserving and privacy-secure sharing of eye images, PrivateEyes supports responsible research and development in AR/VR and other gaze-driven applications.

Aryan Garg, Sizhuo Ma, Mohit Gupta

Capturing high-quality images from only a few detected photons is a fundamental challenge in computational imaging. Single-photon avalanche diode (SPAD) sensors promise high-quality imaging in regimes where conventional cameras fail, but raw quanta frames contain only sparse, noisy, binary photon detections. Recovering a coherent image from a burst of such frames requires handling alignment, denoising, and demosaicing (for color) under noise statistics far outside those assumed by standard restoration pipelines or modern generative models. We present an approach that adapts large text-to-image latent diffusion models to the photon-limited domain of quanta burst imaging. Our method leverages the structural and semantic priors of internet-scale diffusion models while introducing mechanisms to handle Bernoulli photon statistics. By integrating latent-space restoration with burst-level spatio-temporal reasoning, our approach produces reconstructions that are both photometrically faithful and perceptually pleasing, even under high-speed motion. We evaluate the method on synthetic benchmarks and new real-world datasets, including the first color SPAD burst dataset and a challenging Deforming (XD) video benchmark. Across all settings, the approach substantially improves perceptual quality over classical and modern learning-based baselines, demonstrating the promise of adapting large generative priors to extreme photon-limited sensing. Code at https://github.com/Aryan-Garg/gQIR.

Min Yang, Xinwen Zhang, Jialei Tang, Xin Zhou, Kehan Li, Zeyi Huang, Limin Wang

With the great advancement of video generation models, a growing number of content creators and researchers are leveraging these technologies to produce large volumes of human-centric videos for content creation and customized data generation for specific tasks. Although existing video generation models are capable of producing videos with high visual quality, their inadequate understanding of video realism results in generating unrealistic videos. While various evaluators have emerged to assess the quality of generated videos, they are trained from low-quality generated videos and data annotations, leading to misaligned ratings with human preferences. They also lack interpretability due to the absence of chain-of-thought reasoning. To address these issues, we propose VideoRealBench, a comprehensive benchmark for evaluating the realism of generated human-centric videos. We leverage a rating scale designed from human preferences to score videos and provide three-step rationales, thereby creating a finely-annotated dataset VideoRealDataset and proposing an evaluator VideoRealEval capable of providing reliable scores along with detailed rationales. VideoRealEval achieves a Pearson's linear correlation coefficient (PLCC) of 57.07% and a Spearman's rank correlation coefficient (SROCC) of 56.78% on VideoRealDataset, demonstrating closer alignment with human preferences than existing evaluators. Our code and dataset are available at https://github.com/MCG-NJU/VideoRealBench.

Yawar Siddiqui, Duncan Frost, Samir Aroudj, Armen Avetisyan, Henry Howard-Jenkins, Daniel DeTone, Pierre Moulon, Qirui Wu, Zhengqin Li, Julian Straub 等

Recent advances in 3D shape generation have achieved impressive results, but most existing methods rely on clean, unoccluded, and well-segmented inputs. Such conditions are rarely met in real-world scenarios. We present ShapeR, a novel approach for conditional 3D object shape generation from casually captured sequences. Given a image sequence, we leverage off-the-shelf visual-inertial SLAM,3D detection algorithms and VLMs to extract for each object, a set of sparse SLAM points, posed multi-view images, and machine-generated captions. A rectified flow transformer trained to effectively condition on these modalities then generates high-fidelity metric 3D shapes. To ensure robustness to the challenges of casually captured data, we employ a range of techniques including on-the-fly compositional augmentations, a curriculum training scheme spanning object- and scene-level datasets, and strategies to handle background clutter. Additionally, we introduce a new evaluation benchmark comprising 178 in the wild objects across 7 real-world scenes with geometry annotations. Experiments show that ShapeR significantly outperforms existing approaches in this challenging setting, achieving an improvement of 2.7x in Chamfer distance compared to SoTA.

Guangyang Wu, Youran Ding, Xinyu Che, Benyuan Sun, Yi Yang, Xiaohong Liu

Tracking-any-point (TAP) answers query-conditioned correspondence but leaves the dense, all-pairs structure of a video implicit. We formulate All-Pairs Tracking (APT): given a video, predict dense displacement and visibility for every source-target frame pair, from which per-pixel trajectories can be read out. To this end, we propose PairFormer, a feed-forward transformer that addresses APT in a single pass. A spatio-temporal patch encoder computes temporally conditioned features for all frames. \revaddtwo CorrBank builds a learnable correlation bank for each frame pair and produces pairwise motion tokens. A broadcast motion mixer aggregates trajectory-wise context and broadcasts it back to refine the pairwise motion tokens. A trajectory head first predicts coarse dense displacement, visibility, and confidence, and then refines them iteratively to form a coherent all-pairs trajectory field. To support APT at scale, we develop PAIRender, a data platform that synthesizes photo-realistic dynamic scenes with dense annotations. From PAIRender we derive a training set (\pi-R10K) and a benchmark (APT-Bench) with an all-to-all evaluation protocol. Experiments show that PairFormer achieves strong performance on APT-Bench and competitive results on standard TAP benchmarks. Code and dataset will be released upon publication.

Zunkai Dai, Ke Li, Jiajia Liu, Jie Yang, Yuanyuan Qiao

The collection and detection of video anomaly data has long been a challenging problem due to its rare occurrence and spatio-temporal scarcity. Existing video anomaly detection (VAD) methods under perform in open-world scenarios. Key contributing factors include limited dataset diversity, and inadequate understanding of context-dependent anomalous semantics. To address these issues, i) we propose LAVIDA, an end-to-end zero-shot video anomaly detection framework. ii) LAVIDA employs an Anomaly Exposure Sampler that transforms segmented objects into pseudo-anomalies to enhance model adaptability to unseen anomaly categories. It further integrates a Multimodal Large Language Model (MLLM) to bolster semantic comprehension capabilities. Additionally, iii) we design a token compression approach based on reverse attention to handle the spatio-temporal scarcity of anomalous patterns and decrease computational cost. The training process is conducted solely on pseudo anomalies without any VAD data. Evaluations across four benchmark VAD datasets demonstrate that LAVIDA achieves SOTA performance in both frame-level and pixel-level anomaly detection under the zero-shot setting. Our code is available in https://github.com/VitaminCreed/LAVIDA.

Junjie Hu, Tianyang Han, Kai Ma, Jialin Gao, Yang Song, Xianhua He, Junfeng Luo, Xiaoming Wei, Wenqiang Zhang

Recent subject-driven image customization excels in fidelity, yet fine-grained instance-level spatial control remains an elusive challenge, hindering real-world applications. This limitation stems from two factors: a scarcity of scalable, position-annotated datasets, and the entanglement of identity and layout by global attention mechanisms. To this end, we introduce PositionIC, a unified framework for high-fidelity, spatially controllable multi-subject customization. First, we present BMPDS, the first automatic data-synthesis pipeline for position-annotated multi-subject datasets, effectively providing crucial spatial supervision. Second, we design a lightweight, layout-aware diffusion framework that integrates a novel visibility-aware attention mechanism. This mechanism explicitly models spatial relationships via an NeRF-inspired volumetric weight regulation to effectively decouple instance-level spatial embeddings from semantic identity features, enabling precise, occlusion-aware placement of multiple subjects. Extensive experiments demonstrate PositionIC achieves state-of-the-art performance on public benchmarks, setting new records for spatial precision and identity consistency. Our work represents a significant step towards truly controllable, high-fidelity image customization in multi-entity scenarios.Code and data: https://github.com/MeiGen-AI/PositionIC.

Zhipeng Sui, Haiqing Hao, Weihua He, Seng-Hong Lee, Wenhui Wang

Most event-based algorithms typically split the event stream into fixed groups (e.g., fixed time or fixed count) for downstream processing, lacking adaptivity to scene dynamics. Several adaptive partitioning strategies have been proposed, but they are unable to cope well with heterogeneous velocity scenarios (HVS) involving both fast- and slow-moving objects. To address this issue, we propose Adaptive Spatial-Temporal Window (ASTW) strategy, which simultaneously achieves temporal adaptivity and spatial locality in event partitioning. Based on the principle of maximum entropy, we derive a patch-level time window determination criterion and efficiently implement it based on event density and vectorized calculations. Experiments on publicly available event-based object detection and tracking datasets demonstrate that ASTW significantly outperforms existing state-of-the-art partitioning strategies. We also construct HetVel, the first RGB-event dual-modality dataset for HVS, and further highlight the advantages of ASTW on this challenging benchmark. We believe that our ASTW strategy and the constructed HetVel dataset will advance the field of neuromorphic vision.

Yasiru Ranasinghe, Elim Schenck, Florence Yellin, Shuowen Hu, Christopher Funk, Vishal M. Patel

Existing open-vocabulary detectors focus on RGB images and fail to generalize to thermal imagery, where low texture and emissivity variations challenge RGB-based semantics. We present Thermal-Det, the first large language model (LLM) supervised open-vocabulary detector tailored for thermal images. To enable large-scale training, we construct a synthetic dataset by converting GroundingCap-1M into the thermal domain and filtering captions to remove RGB-specific terms, yielding over one million thermally aligned samples with bounding boxes, grounding texts, and detailed captions. Thermal-Det jointly optimizes detection, captioning, and cross-modal distillation objectives. A frozen RGB teacher provides geometric and semantic pseudo-supervision for paired but unlabeled RGB-thermal data, transferring open-vocabulary knowledge without manual annotation. The model further employs a Thermal-Text Alignment Head for text calibration and a Modality-Fused Cross-Attention module for dual-modality reasoning. Unlike prior domain-adaptation methods, the detector is fully fine-tuned to internalize thermal contrast patterns while preserving language alignment. Experiments on public benchmarks show consistent 2-4% AP gains over existing open-vocabulary detectors, establishing a strong foundation for scalable, language-driven thermal perception.

Jinqi Luo, Jinyu Yang, Tal Neiman, Lei Fan, Bing Yin, Son Tran, Mubarak Shah, René Vidal

Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetuning to improve MLLM safety. Nevertheless, such approaches are often ineffective against evolving malicious patterns, may require rerunning the query, or demand heavy computational resources. Steering the activations of a frozen model at inference time has recently emerged as a flexible and effective solution. However, existing steering methods for MLLMs typically handle only a narrow set of safety-related concepts or struggle to adjust specific concepts without affecting others. To address these challenges, we introduce Dictionary-Aligned Concept Control (DACO), a framework that utilizes a curated concept dictionary and a Sparse Autoencoder (SAE) to provide granular control over MLLM activations. First, we curate a dictionary of 15,000 multimodal concepts by retrieving over 400,000 caption-image stimuli and summarizing their activations into concept directions. We name the dataset DACO-400K. Second, we show that the curated dictionary can be used to intervene activations via sparse coding. Third, we propose a new steering approach that uses our dictionary to initialize the training of an SAE and automatically annotate the semantics of the SAE atoms for safeguarding MLLMs. Experiments on multiple MLLMs (e.g., QwenVL, LLaVA, InternVL) across safety benchmarks (e.g., MM-SafetyBench, JailBreakV) show that DACO significantly improves MLLM safety while maintaining general-purpose capabilities.

Jun Zhang, Teng Wang, Yuying Ge, Yixiao Ge, Xinhao Li, Limin Wang

This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models (MLLMs) excel at various video understanding tasks, the recipes for optimizing them for VTG remain under-explored. In this paper, we present TimeLens, a systematic investigation into building MLLMs with strong VTG ability, along two primary dimensions: data quality and algorithmic design. We first expose critical quality issues in existing VTG benchmarks and introduce TimeLens-Bench, comprising meticulously re-annotated versions of three popular benchmarks with strict quality criteria. Our analysis reveals dramatic model re-rankings compared to legacy benchmarks, confirming the unreliability of prior evaluation standards. We also address noisy training data through an automated re-annotation pipeline, yielding TimeLens-100K, a large-scale, high-quality training dataset. Building on our data foundation, we conduct in-depth explorations of algorithmic design principles, yielding a series of meaningful insights and effective yet efficient practices. These include interleaved textual encoding for time representation, a thinking-free reinforcement learning with verifiable rewards (RLVR) approach as the training paradigm, and carefully designed recipes for RLVR training. These efforts culminate in TimeLens models, a family of MLLMs with state-of-the-art VTG performance among open-source models and even surpass proprietary models such as GPT-5 and Gemini-2.5-Flash. All codes, data, and models will be released to facilitate future research.

Huimin Li, Boxuan Hu, Yulin Zhang, Xiuzhuang Zhou, Junlin Hu

Defect synthesis, as a core technology for addressing the problem of few-shot defect classification, has been widely adopted in industrial scenarios. It helps alleviate the problem of insufficient model generalization capability owing to data scarcity by establishing a data augmentation pipeline. Recently, remarkable progress has been achieved in both explicit defect image generation and implicit defect feature synthesis approaches. However, existing methods are always conducted in Euclidean space. Constrained by the flatness of Euclidean space, it is difficult to synthesize defect data containing complex structures. In this paper, we attempt to explore defect generation in hyperbolic space and propose a hyperbolic defect feature synthesis (HypDFS) method. By modeling the potential defect distribution via a small number of hyperbolic defect prototypes and further optimizing the synthetic defect features with the hierarchical defect contrastive loss in hyperbolic space, our HypDFS method can obtain a better generalized defect representation that is more conducive to downstream few-shot defect classification task. Extensive experiments on the MVTec-FS benchmark and standard MTD dataset under the few-shot settings demonstrate that the proposed HypDFS surpasses the Euclidean baseline by a large margin, showing promising prospects for defect synthesis in hyperbolic space.

Yueying Wang, Yiteng Guo, Weidong Zhang, Jie Wen, Liquan Shen, Huaicheng Yan, Xin Xu

Underwater images commonly suffer from foreground-background ambiguity, loss of structural details, and severely reduced contrast, which collectively make underwater object detection (UOD) an inherently challenging task. To handle this issue, we present a residual-guided hierarchical calibration network (RHCNet) designed to achieve more efficient and robust UOD, which comprises a residual-guided feature enhancement module (RGFE) and a hierarchical feature calibration pyramid module (HFCP). Concretely, RHCNet extends the standard ResNet-50 backbone by embedding the RGFE, which effectively strengthens the representation of edge and texture features in blurry regions by jointly leveraging convolutional operations and attention mechanisms to achieve more discriminative feature extraction for UOD. Subsequently, the HFCP integrates a bottom-up semantic enhancement path and a top-down fine-grained feature compensation path, while a K-means clustering-guided feature calibration module is jointly employed to ensure multi-level cross-scale semantic consistency and accurate alignment of salient region features. Extensive experiments on the DUO and UTDAC benchmark datasets demonstrated that our RHCNet attains the highest AP scores of 70.53% and 53.35%, respectively. Besides, our RHCNet also maintains excellent detection accuracy and strong generalization capability on the COCO dataset for terrestrial scenarios. The code is available at https://github.com/YitengGuo/RHCNet.

Kartik Kuckreja, Parul Gupta, Muhammad Haris Khan, Abhinav Dhall

Deepfake detection models often generate natural-language explanations, yet their reasoning is frequently ungrounded in visual evidence, limiting reliability. Existing evaluations measure classification accuracy but overlook reasoning fidelity. We propose DeepfakeJudge, a framework for scalable reasoning supervision and evaluation, that integrates an out-of-distribution benchmark containing recent generative and editing forgeries, a human-annotated subset with visual reasoning labels, and a suite of evaluation models, that specialize in evaluating reasoning rationales without the need for explicit ground truth reasoning rationales. The Judge is optimized through a bootstrapped generator-evaluator process that scales human feedback into structured reasoning supervision and supports both pointwise and pairwise evaluation. On the proposed meta-evaluation benchmark, our reasoning-bootstrapped model achieves an accuracy of 96.2%, outperforming \texttt 30x larger baselines. The reasoning judge attains very high correlation with human ratings and 98.9% percent pairwise agreement on the human annotated meta-evaluation subset. These results establish reasoning fidelity as a quantifiable dimension of deepfake detection and demonstrate scalable supervision for interpretable deepfake reasoning. Our user study indicates that humans prefer reasonings generated by our framework 70% of the time, in faithfullness, groundedness and usefulness compared to other models and datasets. All of our datasets, models, and codebase will be open-sourced.

Zhaoyang Li, Zhan Ling, Yuchen Zhou, Litian Gong, Erdem Biyik, Hao Su

Large Vision-Language Models (LVLMs) excel at captioning, visual question answering, and robotics by combining vision and language, yet they often miss obvious objects or hallucinate nonexistent ones in atypical scenes. We examine these failures through the lens of uncertainty, focusing on contextual incongruity, where objects appear unexpectedly or fail to appear in expected contexts, and show that such cases increase recognition difficulty for state-of-the- art LVLMs. To study this regime, we introduce the Object Recognition in Incongruous Context (ORIC) framework, which constructs incongruous object-context pairs through two complementary strategies: (1) LLM-guided sampling to identify hard-to-recognize objects present in the image and (2) CLIP-guided sampling to mine plausible but absent ones. Applied to MSCOCO, ORIC creates ORIC-Bench and ORIC-style training data. Evaluating 18 LVLMs and 2 open-vocabulary detectors reveals significant degradation and bias under incongruous contexts. Visual Reinforcement Fine-Tuning of Qwen3-VL-8B-Instruct on 600 ORIC sam- ples improves performance on ORIC-Bench, AMBER, and HallusionBench. Overall, we show that contextual incongruity is a key source of uncertainty and provide tools for more reliable LVLMs. The dataset and code are publicly available at https://github.com/ZhaoyangLi-1/ORIC.

Ujjwal Upadhyay, Mukul Ranjan, Zhiqiang Shen, Mohamed Elhoseiny

Recent advances in vision-language models (VLMs) have made impressive strides in understanding spatio-temporal relationships in videos. However, when spatial information is obscured, these models struggle to capture purely temporal patterns. We introduce SpookyBench, a benchmark where information is encoded solely in temporal sequences of noise-like frames, mirroring natural phenomena from biological signaling to covert communication. Interestingly, while humans can recognize shapes, text, and patterns in these sequences with over 98% accuracy, state-of-the-art VLMs achieve 0% accuracy. This highlights a critical limitation: an over-reliance on frame-level spatial features and an inability to extract meaning from temporal cues. Overcoming this limitation will require novel architectures or training paradigms that decouple spatial dependencies from temporal processing. Our systematic analysis shows that this issue persists across model scales and architectures. We release SpookyBench to catalyze research in temporal pattern recognition and bridge the gap between human and machine video understanding. Dataset and code are available on the project website.

Enhui Ma, Jiahuan Zhang, Guantian Zheng, Tao Tang, Shengbo Eben Li, Yuhang Lu, Xia Zhou, Xueyang Zhang, Yifei Zhan, Kun Zhan 等

Multimodal Large Language Models (MLLMs) are rapidly becoming the intelligence brain of end-to-end autonomous driving systems. A key challenge is to assess whether MLLMs can truly understand and follow complex real-world traffic rules. However, existing benchmarks mainly focus on single-rule scenarios like traffic sign recognition, neglecting the complexity of multi-rule concurrency and conflicts in real driving. Consequently, models perform well on simple tasks but often fail or violate rules in real world complex situations. To bridge this gap, we propose DriveCombo, a text and vision-based benchmark for compositional traffic rule reasoning. Inspired by human drivers' cognitive development, we propose a systematic Five-Level Cognitive Ladder that evaluates reasoning from single-rule understanding to multi-rule integration and conflict resolution, enabling quantitative assessment across cognitive stages. We further propose a Rule2Scene Agent that maps language-based traffic rules to dynamic driving scenes through rule crafting and scene generation, enabling scene-level traffic rule visual reasoning. Evaluations of 14 mainstream MLLMs reveal a pronounced decline in performance as task difficulty increases, especially in the rule conflict resolution task. After splitting the dataset and fine-tuning on the training set, we further observe substantial improvements in both traffic rule reasoning and downstream planning capabilities. These results highlight the effectiveness of DriveCombo in advancing compliant and intelligent autonomous driving systems.

Tarun Gehlaut, Difan Liu, Charu Bansal, Krutik Malani, Souymodip Chakraborty, Ankit Phogat, Matthew Fisher, Vineet Batra

Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluated on synthetic benchmarks, where clean SVGs are rasterized at high resolution and then re-vectorized. As a result, these methods generalize poorly to real-world scenarios, such as images with unknown rasterization methods or those generated by text-to-image models.We introduce VectorArk, a new VLM-based model designed for robust and practical image vectorization. VectorArk employs a novel rounded polygon representation that simplifies the learning process while naturally producing smooth, visually appealing primitives. We also propose a degradation model that enhances robustness across diverse and imperfect inputs.Our experiments show that, in contrast to previous methods, VectorArk achieves superior geometric completeness and artifact suppression across multiple datasets, with comprehensive ablations validating the contribution of each component.

Jing Bi, Filippos Bellos, Junjia Guo, Yayuan Li, Chao Huang, Yunlong Tang, Luchuan Song, Susan Liang, Zhongfei Zhang, Jason J. Corso 等

Test-time "thinking" (i.e., generating explicit intermediate reasoning chains) is known to boost performance in large language models and has recently shown strong gains for large vision-language models (LVLMs). However, despite these promising results, there is still no systematic analysis of how thinking actually affects visual reasoning. We provide the first such analysis with a large-scale, controlled comparison of thinking for LVLMs, evaluating 10 variants from the InternVL3.5 and Qwen3-VL families on MMMUval under generous token budgets and multi-pass decoding. We show that more thinking is not always better: long chains often yield long-wrong trajectories that ignore the image and underperform the same models run in standard instruct mode. A deeper analysis reveals that certain short "lookback" phrases, which explicitly refer back to the image, are strongly enriched in successful trajectories and correlate with better visual grounding. Building on this insight, we propose uncertainty-guided lookback, a training-free decoding strategy that combines an uncertainty signal with adaptive lookback prompts and breadth search. Our method improves overall MMMU performance, delivers the largest gains in categories where standard thinking is weak, and outperforms several strong decoding baselines, setting a new state of the art under fixed model families and token budgets. We further show that this decoding strategy generalizes, yielding consistent improvements on five additional benchmarks, including two broad multimodal suites and math-focused visual reasoning datasets.

Huidong Feng, Wentao Chen, Jie Chen, Xinqi Cai, Ruolong Ma, Yinglin Zheng, Yuxin Lin, Ming Zeng

With the rapid advancement of artificial intelligence generated content (AIGC) technologies, video forgery has become increasingly prevalent, posing new challenges to public discourse and societal security. Despite remarkable progress in existing deepfake detection methods, AIGC forgery detection remains challenging, as existing datasets mainly rely on open-source video generation models with quality far below commercial AIGC systems. Even datasets containing a few commercial samples often retain visible watermarks, compromising authenticity and hindering model generalization to high-fidelity AIGC videos. To address these issues, we introduce CoCoVideo-26K, a contrastive, commercial-model-based AIGC video dataset covering 13 mainstream commercial generators and providing semantically aligned real-fake video pairs. This dataset enables deeper exploration of the differences between authentic and high-quality synthetic videos, establishes a new benchmark for highly realistic video forgery detection. Building on this dataset, we propose CoCoDetect, a detection framework integrating contrastive learning with confidence-gated multimodal large language model (MLLM) inference. An R3D-18 backbone extracts spatio-temporal representations, while a confidence gate routes uncertain cases to an MLLM for reasoning about physical plausibility and scene consistency. Extensive experiments on CoCoVideo-26K and public benchmarks demonstrate state-of-the-art performance, validating the framework's robustness and generality. Our code and dataset are available at https://github.com/DonoToT/CoCoVideo.