Real-world video editing demands not only expert knowledge of cinematic techniques but also multimodal reasoning to select, align, and combine footage into coherent narratives. While recent Large Multimodal Models (LMMs) have shown remarkable progress in general video understanding, their abilities in multi-video reasoning and operational editing workflows remain largely unexplored. We introduce VEBENCH, the first comprehensive benchmark designed to evaluate both editing knowledge understanding and operational reasoning in realistic video editing scenarios. VEBENCH contains 3.9K high-quality edited videos (over 257 hours) and 3,080 human-verified QA pairs, built through a three-round human-AI collaborative annotation pipeline that ensures precise temporal labeling and semantic consistency. It features two complementary QA tasks: 1) Video Editing Technique Recognition, assessing models' ability to identify 7 editing techniques using multimodal cues; and 2) Video Editing Operation Simulation, modeling real-world editing workflows by requiring the selection and temporal localization of relevant clips from multiple candidates. Extensive experiments across proprietary (e.g., Gemini-2.5-Pro) and open-source LMMs reveal a large gap between current model performance and human-level editing cognition. These results highlight the urgent need for bridging video understanding with creative operational reasoning. We envision VEBENCH as a foundation for advancing intelligent video editing systems and driving future research on complex reasoning.

Humans naturally share information with those they are connected to, and video has become one of the dominant mediums for communication and expression on the Internet. To support the creation of high-quality large-scale video content, a modern pipeline requires a comprehensive understanding of both the raw input materials (e.g., the unedited footage captured by cameras) and the editing components (e.g., visual effects). In video editing scenarios, models must process multiple modalities (e.g., vision, audio, text) with strong background knowledge and handle flexible input lengths (e.g., hour-long raw videos), which poses significant challenges for traditional models. In this report, we introduce Vidi, a family of Large Multimodal Models (LMMs) for a wide range of video understand editing scenarios. The first release focuses on temporal retrieval, i.e., identifying the time ranges within the input videos corresponding to a given text query, which plays a critical role in intelligent editing. The model is capable of processing hour-long videos with strong temporal understanding capability, e.g., retrieve time ranges for certain queries. To support a comprehensive evaluation in real-world scenarios, we also present the VUE-TR benchmark, which introduces five key advancements. 1) Video duration: significantly longer than videos of existing temporal retrival datasets, 2) Audio support: includes audio-based queries, 3) Query format: diverse query lengths/formats, 4) Annotation quality: ground-truth time ranges are manually annotated. 5) Evaluation metric: a refined IoU metric to support evaluation over multiple time ranges. Remarkably, Vidi significantly outperforms leading proprietary models, e.g., GPT-4o and Gemini, on the temporal retrieval task, indicating its superiority in video editing scenarios.

Video has emerged as the primary medium for communication and creativity on the Internet, driving strong demand for scalable, high-quality video production. Vidi models continue to evolve toward next-generation video creation and have achieved state-of-the-art performance in multimodal temporal retrieval (TR). In its second release, Vidi2 advances video understanding with fine-grained spatio-temporal grounding (STG) and extends its capability to video question answering (Video QA), enabling comprehensive multimodal reasoning. Given a text query, Vidi2 can identify not only the corresponding timestamps but also the bounding boxes of target objects within the output time ranges. To enable comprehensive evaluation of STG, we introduce a new benchmark, VUE-STG, which offers critical improvements over existing STG datasets. In addition, we upgrade the previous VUE-TR benchmark to VUE-TR-V2, achieving a more balanced duration and query distribution. Remarkably, the Vidi2 model substantially outperforms leading proprietary systems, such as Gemini 3 Pro Preview and GPT-5, on both VUE-TR-V2 and VUE-STG, while achieving competitive results with popular open-source models with similar scale on video QA benchmarks. The latest Vidi2.5 offers significantly stronger STG capability and slightly better TR and Video QA performance over Vidi2. This update also introduces a Vidi2.5-Think model to handle plot understanding with complex plot reasoning. To comprehensively evaluate the performance of plot understanding, we propose VUE-PLOT benchmark with two tracks, Character and Reasoning. Notably, Vidi2.5-Think outperforms Gemini 3 Pro Preview on fine-grained character understanding with comparable performance on complex plot reasoning. Furthermore, we demonstrate the effectiveness of Vidi2.5 on a challenging real-world application, video editing planning.

Steller sea lions, who tend to live on the rocky shores and coastal waters of the subarctic, have faced declining populations since the 1970s and were listed as endangered in 1997 within distinct western population centers. Monitoring their populations is therefore crucial to future management and setting government regulations. In this paper, we present a novel dataset for sea lion detection and identification across multiple cameras, which includes different labels for age and sex sub-classification, alongside related distractor animal species (such as fur seals). The data was collected from mixed 1- and 3-camera systems, mounted on both fixed-wing airplanes and unmanned systems. The performance of several algorithms is compared on this dataset, including novel detector ensembles and multi-sensor temporal tracking methods, which were developed in order to produce accurate population counts.

The emerging video LMMs (Large Multimodal Models) have achieved significant improvements on generic video understanding in the form of VQA (Visual Question Answering), where the raw videos are captured by cameras. However, a large portion of videos in real-world applications are edited videos, e.g., users usually cut and add effects/modifications to the raw video before publishing it on social media platforms. The edited videos usually have high view counts but they are not covered in existing benchmarks of video LMMs, i.e., ActivityNet-QA, or VideoChatGPT benchmark. In this paper, we leverage the edited videos on a popular short video platform, i.e., TikTok, and build a video VQA benchmark (named EditVid-QA) covering four typical editing categories, i.e., effect, funny, meme, and game. Funny and meme videos benchmark nuanced understanding and high-level reasoning, while effect and game evaluate the understanding capability of artificial design. Most of the open-source video LMMs perform poorly on the EditVid-QA benchmark, indicating a huge domain gap between edited short videos on social media and regular raw videos. To improve the generalization ability of LMMs, we collect a training set for the proposed benchmark based on both Panda-70M/WebVid raw videos and small-scale TikTok/CapCut edited videos, which boosts the performance on the proposed EditVid-QA benchmark, indicating the effectiveness of high-quality training data. We also identified a serious issue in the existing evaluation protocol using the GPT-3.5 judge, namely a "sorry" attack, where a sorry-style naive answer can achieve an extremely high rating from the GPT judge, e.g., over 4.3 for correctness score on VideoChatGPT evaluation protocol. To avoid the "sorry" attacks, we evaluate results with GPT-4 judge and keyword filtering. The dataset is released at https://github.com/XenonLamb/EditVid-QA.

Managing novelty in perception-based human activity recognition (HAR) is critical in realistic settings to improve task performance over time and ensure solution generalization outside of prior seen samples. Novelty manifests in HAR as unseen samples, activities, objects, environments, and sensor changes, among other ways. Novelty may be task-relevant, such as a new class or new features, or task-irrelevant resulting in nuisance novelty, such as never before seen noise, blur, or distorted video recordings. To perform HAR optimally, algorithmic solutions must be tolerant to nuisance novelty, and learn over time in the face of novelty. This paper 1) formalizes the definition of novelty in HAR building upon the prior definition of novelty in classification tasks, 2) proposes an incremental open world learning (OWL) protocol and applies it to the Kinetics datasets to generate a new benchmark KOWL-718, 3) analyzes the performance of current stateof-the-art HAR models when novelty is introduced over time, 4) provides a containerized and packaged pipeline for reproducing the OWL protocol and for modifying for any future updates to Kinetics. The experimental analysis includes an ablation study of how the different models perform under various conditions as annotated by Kinetics-AVA. The code may be used to analyze different annotations and subsets of the Kinetics datasets in an incremental open world fashion, as well as be extended as further updates to Kinetics are released.

Biometric recognition from security camera video is a challenging problem when the individuals change clothes or when they are partly occluded. Others have recently demonstrated that CLIP's visual encoder performs well in this domain, but existing methods fail to make use of the model's text encoder or temporal information available in video. In this paper, we present VCLIP, a method for person identification in videos captured in challenging poses and with changes to a person's clothing. Harnessing the power of pre-trained vision-language models, we Jointly train a temporal fusion network while fine-tuning the visual encoder. To leverage the cross-modal embedding space, we use learned biometric pedestrian attribute features to further enhance our model's person re-identification (Re-ID) ability. We demonstrate significant performance improvements via experiments with the MEVID and CCVID datasets, particularly in the more challenging clothes-changing conditions. In support of this and future methods that use textual attributes for Re-ID with multimodal models, we release a dataset of annotated pedestrian attributes for the popular MEVID dataset [4].

Multiview subspace clustering aims to discover the inherent structure of data by fusing multiple views of complementary information. Most existing methods first extract multiple types of handcrafted features and then learn a joint affinity matrix for clustering. The disadvantage of this approach lies in two aspects: 1) multiview relations are not embedded into feature learning and 2) the end-to-end learning manner of deep learning is not suitable for multiview clustering. Even when deep features have been extracted, it is a nontrivial problem to choose a proper backbone for clustering on different datasets. To address these issues, we propose the multiview deep subspace clustering networks (MvDSCNs), which learns a multiview self-representation matrix in an end-to-end manner. The MvDSCN consists of two subnetworks, i.e., a diversity network (Dnet) and a universality network (Unet). A latent space is built using deep convolutional autoencoders, and a self-representation matrix is learned in the latent space using a fully connected layer. Dnet learns view-specific self-representation matrices, whereas Unet learns a common self-representation matrix for all views. To exploit the complementarity of multiview representations, the Hilbert-Schmidt independence criterion (HSIC) is introduced as a diversity regularizer that captures the nonlinear, high-order interview relations. Because different views share the same label space, the self-representation matrices of each view are aligned to the common one by universality regularization. The MvDSCN also unifies multiple backbones to boost clustering performance and avoid the need for model selection. Experiments demonstrate the superiority of the MvDSCN.

Managing novelty in perception-based human activity recognition (HAR) is critical in realistic settings to improve task performance over time and ensure solution generalization outside of prior seen samples. Novelty manifests in HAR as unseen samples, activities, objects, environments, and sensor changes, among other ways. Novelty may be task-relevant, such as a new class or new features, or task-irrelevant resulting in nuisance novelty, such as never before seen noise, blur, or distorted video recordings. To perform HAR optimally, algorithmic solutions must be tolerant to nuisance novelty, and learn over time in the face of novelty. This paper 1) formalizes the definition of novelty in HAR building upon the prior definition of novelty in classification tasks, 2) proposes an incremental open world learning (OWL) protocol and applies it to the Kinetics datasets to generate a new benchmark KOWL-718, 3) analyzes the performance of current state-of-the-art HAR models when novelty is introduced over time, 4) provides a containerized and packaged pipeline for reproducing the OWL protocol and for modifying for any future updates to Kinetics. The experimental analysis includes an ablation study of how the different models perform under various conditions as annotated by Kinetics-AVA. The code may be used to analyze different annotations and subsets of the Kinetics datasets in an incremental open world fashion, as well as be extended as further updates to Kinetics are released.

Both few-shot learning and domain adaptation sub-fields in Computer Vision have seen significant recent progress in terms of the availability of state-of-the-art algorithms and datasets. Frameworks have been developed for each sub-field; however, building a common system or framework that combines both is something that has not been explored. As part of our research, we present the first unified framework that combines domain adaptation for the few-shot learning setting across 3 different tasks - image classification, object detection and video classification. Our framework is highly modular with the capability to support few-shot learning with/without the inclusion of domain adaptation depending on the algorithm. Furthermore, the most important configurable feature of our framework is the on-the-fly setup for incremental n-shot tasks with the optional capability to configure the system to scale to a traditional many-shot task. With more focus on Self-Supervised Learning (SSL) for current few-shot learning approaches, our system also supports multiple SSL pre-training configurations. To test our framework's capabilities, we provide benchmarks on a wide range of algorithms and datasets across different task and problem settings. The code is open source has been made publicly available here: https://gitlab.kitware.com/darpa_learn/learn

Most action recognition datasets and algorithms assume a closed world, where all test samples are instances of the known classes. In open set problems, test samples may be drawn from either known or unknown classes. Existing open set action recognition methods are typically based on extending closed set methods by adding post hoc analysis of classification scores or feature distances and do not capture the relations among all the video clip elements. Our approach uses the reconstruction error to determine the novelty of the video since unknown classes are harder to put back together and thus have a higher reconstruction error than videos from known classes. We refer to our solution to the open set action recognition problem as "Humpty Dumpty", due to its reconstruction abilities. Humpty Dumpty is a novel graph-based autoencoder that accounts for contextual and semantic relations among the clip pieces for improved reconstruction. A larger reconstruction error leads to an increased likelihood that the action can not be reconstructed, i.e., can not put Humpty Dumpty back together again, indicating that the action has never been seen before and is novel/unknown. Extensive experiments are performed on two publicly available action recognition datasets including HMDB-51 and UCF-101, showing the state-of-the-art performance for open set action recognition.

In order to recognize people across long distances and from elevated viewpoints, biometric systems must handle the challenges of imaging through atmospheric turbulence and non-frontal presentations, in addition to the traditional A-PIE challenges of aging, pose, illumination, and expression. While individual biometric modalities such as facial appearance, gait, and whole body appearance each have a role to play, no single modality can address all of these challenges. This paper describes a novel multi-modal biometric recognition system that addresses the challenges of atmospheric turbulence, occlusions, and elevated viewpoints by combining these modalities. We demonstrate our system on both $R G B$ video-based identity verification and both open and closed-world search.

In this paper, we present the Multi-view Extended Videos with Identities (MEVID) dataset for large-scale, video person re-identification (ReID) in the wild. To our knowledge, MEVID represents the most-varied video person ReID dataset, spanning an extensive indoor and outdoor environment across nine unique dates in a 73-day window, various camera viewpoints, and entity clothing changes. Specifically, we label the identities of 158 unique people wearing 598 outfits taken from 8, 092 tracklets, average length of about 590 frames, seen in 33 camera views from the very large-scale MEVA person activities dataset. While other datasets have more unique identities, MEVID emphasizes a richer set of information about each individual, such as: 4 outfits/identity vs. 2 outfits/identity in CCVID, 33 viewpoints across 17 locations vs. 6 in 5 simulated locations for MTA, and 10 million frames vs. 3 million for LS-VID. Being based on the MEVA video dataset, we also inherit data that is intentionally demographically balanced to the continental United States. To accelerate the annotation process, we developed a semi-automatic annotation framework and GUI that combines state-of-the-art real-time models for object detection, pose estimation, person ReID, and multi-object tracking. We evaluate several state-of-the-art methods on MEVID challenge problems and comprehensively quantify their robustness in terms of changes of outfit, scale, and background location. Our quantitative analysis on the realistic, unique aspects of MEVID shows that there are significant remaining challenges in video person ReID and indicates important directions for future research.

Existing methods for open set action recognition focus on novelty detection that assumes video clips show a single action, which is unrealistic in the real world. We propose a new method for open set action recognition and novelty detection via MUlti-Label Evidential learning (MULE), that goes beyond previous novel action detection methods by addressing the more general problems of single or multiple actors in the same scene, with simultaneous action(s) by any actor. Our Beta Evidential Neural Network estimates multi-action uncertainty with Beta densities based on actor-context-object relation representations. An evidence debiasing constraint is added to the objective function for optimization to reduce the static bias of video representations, which can incorrectly correlate predictions and static cues. We develop a primal-dual average scheme update-based learning algorithm to optimize the proposed problem and provide corresponding theoretical analysis. Besides, uncertainty and belief-based novelty estimation mechanisms are formulated to detect novel actions. Extensive experiments on two real-world video datasets show that our proposed approach achieves promising performance in single/multi-actor, single/multi-action settings. Our code and models are released at https://github.com/charliezhaoyinpeng/mule.

Person re-identification (Re-ID) on aerial-ground platforms has emerged as an intriguing topic within computer vision, presenting a plethora of unique challenges. High-flying altitudes of aerial cameras make persons appear differently in terms of viewpoints, poses, and resolution compared to the images of the same person viewed from ground cameras. Despite its potential, few algorithms have been developed for person re-identification on aerial-ground data, mainly due to the absence of comprehensive datasets. In response, we have collected a large-scale dataset and organized the Aerial-Ground person Re-IDentification Challenge (AG-ReID2023) to foster advancements in the field. The dataset comprises 100, 502 images with 1, 615 unique identities, including 51, 530 training images featuring 807 identities. The test set is divided into two subsets: Aerial to Ground (808 ids, 4, 348 query images, 19, 259 gallery images) and Ground to Aerial (808 ids, 4, 151 query images, 21, 214 gallery images). In addition, we manually annotate individuals with their matching IDs across cameras and provide 15 soft attribute labels. The AG-ReID2023 Challenge in conjunction with the 7th IEEE International Joint Conference on Biometrics (IJCB) has garnered interest from numerous institutes, resulting in the submission of five distinct algorithms. We provide an in-depth examination of the evaluation outcomes and present our findings from the contest. For additional details, kindly refer to the official website(1).

Novel object detection in remote sensing is challenging due to small objects, background clutter and open-set recognition. To discover and identify objects that are not within the set of known classes in training, we developed the extreme value theory-based novel object detection framework. Specifically, we first employed the state-of-the-art object detector to extract object detections. Then, the extreme value model (EVM) is trained based on the features of extracted detections. Thus our method can characterize the distribution of outliers in the known classes-based distributions to classify novel objects. If the novelty score is larger than the pre-set threshold, we assign this sample to novel classes; otherwise the sample is classified by the original object detector. To adapt to our task, we hold out a novel set of 18 of overall 60 classes in the xView dataset in satellite imagery. The experimental results on the xView dataset show the effectiveness of our proposed approach over traditional softmax thresholding.

Domain adaptive object detection is challenging due to distinctive data distribution between source domain and target domain. In this paper, we propose a unified multi-granularity alignment based object detection framework towards domain-invariant feature learning. To this end, we encode the dependencies across different granularity perspectives including pixel-, instance-, and category-levels simultaneously to align two domains. Based on pixel-level feature maps from the backbone network, we first develop the omni-scale gated fusion module to aggregate discriminative representations of instances by scale-aware convolutions, leading to robust multi-scale object detection. Meanwhile, the multi-granularity discriminators are proposed to identify which domain different granularities of samples(i.e., pixels, instances, and categories) come from. Notably, we leverage not only the instance discriminability in different categories but also the category consistency between two domains. Extensive experiments are carried out on multiple domain adaptation scenarios, demonstrating the effectiveness of our framework over state-of-the-art algorithms on top of anchor-free FCOS and anchor-based Faster RCNN detectors with different backbones.

The goal of person search is to localize a target person from a gallery set of scene images, which is extremely challenging due to large scale variations, pose/viewpoint changes, and occlusions. In this paper, we propose the Cascade Occluded Attention Transformer (COAT) for end-to-end person search. Our three-stage cascade design focuses on detecting people in the first stage, while later stages simultaneously and progressively refine the representation for person detection and re-identification. At each stage the occluded attention transformer applies tighter intersection over union thresholds, forcing the network to learn coarse-to-fine pose/scale invariant features. Meanwhile, we calculate each detection's occluded attention to differentiate a person's tokens from other people or the background. In this way, we simulate the effect of other objects occluding a person of interest at the token-level. Through comprehensive experiments, we demonstrate the benefits of our method by achieving state-of-the-art performance on two benchmark datasets.

Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. In this paper, we first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. After that, we describe our VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions. We expect the benchmark largely boost the research and development in video analysis on drone platforms. All the datasets and experimental results can be downloaded from https://github.com/VisDrone/VisDrone-Dataset.