The recent advancement in video temporal grounding (VTG) has significantly enhanced fine-grained video understanding, primarily driven by multimodal large language models (MLLMs). With superior multimodal comprehension and reasoning abilities, VTG approaches based on MLLMs (VTG-MLLMs) are gradually surpassing traditional fine-tuned methods. They not only achieve competitive performance but also excel in generalization across zero-shot, multi-task, and multi-domain settings. Despite extensive surveys on general video-language understanding, comprehensive reviews specifically addressing VTG-MLLMs remain scarce. To fill this gap, this survey systematically examines current research on VTG-MLLMs through a three-dimensional taxonomy: 1) the functional roles of MLLMs, highlighting their architectural significance; 2) training paradigms, analyzing strategies for temporal reasoning and task adaptation; and 3) video feature processing techniques, which determine spatiotemporal representation effectiveness. We further discuss benchmark datasets, evaluation protocols, and summarize empirical findings. Finally, we identify existing limitations and propose promising research directions.

Recent advances in Large Multi-modal Models (LMMs) have demonstrated their remarkable success as general-purpose multi-modal assistants, with particular focuses on holistic image- and video-language understanding. Conversely, less attention has been given to scaling fine-grained pixel-level understanding capabilities, where the models are expected to realize pixel-level alignment between visual signals and language semantics. Some previous studies have applied LMMs to related tasks such as region-level captioning and referring expression segmentation. However, these models are limited to performing either referring or segmentation tasks independently and fail to integrate these fine-grained perception capabilities into visual reasoning. To bridge this gap, we propose UniPixel, a large multi-modal model capable of flexibly comprehending visual prompt inputs and generating mask-grounded responses. Our model distinguishes itself by seamlessly integrating pixel-level perception with general visual understanding capabilities. Specifically, UniPixel processes visual prompts and generates relevant masks on demand, and performs subsequent reasoning conditioning on these intermediate pointers during inference, thereby enabling fine-grained pixel-level reasoning. The effectiveness of our approach has been verified on 10 benchmarks across a diverse set of tasks, including pixel-level referring/segmentation and object-centric understanding in images/videos. A novel PixelQA task that jointly requires referring, segmentation, and question answering is also designed to verify the flexibility of our method.

The task of instance segmentation in remote sensing images, aiming at performing per-pixel labeling of objects at the instance level, is of great importance for various civil applications. Despite previous successes, most existing instance segmentation methods designed for natural images encounter sharp performance degradations when they are directly applied to top-view remote sensing images. Through careful analysis, we observe that the challenges mainly come from the lack of discriminative object features due to severe scale variations, low contrasts, and clustered distributions. In order to address these problems, a novel context aggregation network (CATNet) is proposed to improve the feature extraction process. The proposed model exploits three lightweight plug-and-play modules, namely, dense feature pyramid network (DenseFPN), spatial context pyramid (SCP), and hierarchical region of interest extractor (HRoIE), to aggregate global visual context at feature, spatial, and instance domains, respectively. DenseFPN is a multi-scale feature propagation module that establishes more flexible information flows by adopting interlevel residual connections, cross-level dense connections, and feature reweighting strategy. Leveraging the attention mechanism, SCP further augments the features by aggregating global spatial context into local regions. For each instance, HRoIE adaptively generates RoI features for different downstream tasks. Extensive evaluations of the proposed scheme on iSAID, DIOR, NWPU VHR-10, and HRSID datasets demonstrate that the proposed approach outperforms state-of-the-arts under similar computational costs. Source code and pretrained models are available at https://github.com/yeliudev/CATNet.

Recent advances in Video Large Language Models (Video-LLMs) have demonstrated their great potential in general-purpose video understanding. To verify the significance of these models, a number of benchmarks have been proposed to diagnose their capabilities in different scenarios. However, existing benchmarks merely evaluate models through video-level question-answering, lacking fine-grained event-level assessment and task diversity. To fill this gap, we introduce E.T. Bench (Event-Level & Time-Sensitive Video Understanding Benchmark), a large-scale and high-quality benchmark for open-ended event-level video understanding. Categorized within a 3-level task taxonomy, E.T. Bench encompasses 7.3K samples under 12 tasks with 7K videos (251.4h total length) under 8 domains, providing comprehensive evaluations. We extensively evaluated 8 Image-LLMs and 12 Video-LLMs on our benchmark, and the results reveal that state-of-the-art models for coarse-level (video-level) understanding struggle to solve our fine-grained tasks, e.g., grounding event-of-interests within videos, largely due to the short video context length, improper time representations, and lack of multi-event training data. Focusing on these issues, we further propose a strong baseline model, E.T. Chat, together with an instruction-tuning dataset E.T. Instruct 164K tailored for fine-grained event-level understanding. Our simple but effective solution demonstrates superior performance in multiple scenarios.

Location recommendation plays a vital role in improving users' travel experience. The timestamp of the POI to be predicted is of great significance, since a user will go to different places at different times. However, most existing methods either do not use this kind of temporal information, or just implicitly fuse it with other contextual information. In this paper, we revisit the problem of location recommendation and point out that explicitly modeling temporal information is a great help when the model needs to predict not only the next location but also further locations. In addition, state-of-the-art methods do not make effective use of geographic information and suffer from the hard boundary problem when encoding geographic information by gridding. To this end, a Temporal Prompt-based and Geography-aware (TPG) framework is proposed. The temporal prompt is firstly designed to incorporate temporal information of any further check-in. A shifted window mechanism is then devised to augment geographic data for addressing the hard boundary problem. Via extensive comparisons with existing methods and ablation studies on five real-world datasets, we demonstrate the effectiveness and superiority of the proposed method under various settings. Most importantly, our proposed model has the superior ability of interval prediction. In particular, the model can predict the location that a user wants to go to at a certain time while the most recent check-in behavioral data is masked, or it can predict specific future check-in (not just the next one) at a given timestamp.

Finding relevant moments and highlights in videos according to natural language queries is a natural and highly valuable common need in the current video content explosion era. Nevertheless, jointly conducting moment retrieval and highlight detection is an emerging research topic, even though its component problems and some related tasks have already been studied for a while. In this paper, we present the first unified framework, named Unified Multi-modal Transformers (UMT), capable of realizing such joint optimization while can also be easily degenerated for solving individual problems. As far as we are aware, this is the first scheme to integrate multi-modal (visual-audio) learning for either joint optimization or the individual moment retrieval task, and tackles moment retrieval as a keypoint detection problem using a novel query generator and query decoder. Extensive comparisons with existing methods and ablation studies on QVHighlights, Charades-STA, YouTube Highlights, and TVSum datasets demonstrate the effectiveness, superiority, and flexibility of the proposed method under various settings. Source code and pre-trained models are available at https://github.com/TencentARC/UMT.

Urban water quality is of great importance to our daily lives. Prediction of urban water quality help control water pollution and protect human health. However, predicting the urban water quality is a challenging task since the water quality varies in urban spaces non-linearly and depends on multiple factors, such as meteorology, water usage patterns, and land uses. In this article, we forecast the water quality of a station over the next few hours from a data-driven perspective, using the water quality data, and water hydraulic data reported by existing monitor stations and a variety of data sources we observed in the city, such as meteorology, pipe networks, structure of road networks, and point of interests (POIs). First, we identify the influential factors that affect the urban water quality via extensive experiments. Second, we present a multi-task multi-view learning method to fuse those multiple datasets from different domains into an unified learning model. We evaluate our method with real-world datasets, and the extensive experiments verify the advantages of our method over other baselines and demonstrate the effectiveness of our approach.

Spatially fine-grained urban flow data is critical for smart city efforts. Though fine-grained information is desirable for applications, it demands much more resources for the underlying storage system compared to coarse-grained data. To bridge the gap between storage efficiency and data utility, in this paper, we aim to infer fine-grained flows throughout a city from their coarse-grained counterparts. This task exhibits two challenges: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a model entitled UrbanFM which consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs that uses a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influence of different external factors. This structure provides outstanding effectiveness and efficiency for small scale upsampling. However, the single-pass upsampling used by UrbanFM is insufficient at higher upscaling rates. Therefore, we further present UrbanPy, a cascading model for progressive inference of fine-grained urban flows by decomposing the original tasks into multiple subtasks. Compared to UrbanFM, such an enhanced structure demonstrates favorable performance for larger-scale inference tasks.

Learning semantically coherent location embeddings can benefit downstream applications such as human mobility prediction. However, the conflation of geographic and semantic attributes of a location can harm such coherence, especially when semantic labels are not provided for the learning. To resolve this problem, in this paper, we present a novel unsupervised method for learning location embeddings from human trajectories. Our method advances traditional transition-based techniques in two ways: 1) we alleviate the disturbance of geographic attributes on the semantics by disentangling the two spaces; and 2) we incorporate spatio-temporal attributes and regular visiting patterns of trajectories to capture the semantics more accurately. Moreover, we present the first quantitative evaluation on location embeddings by introducing an original query-based metric, and we apply the metric in experiments on two Foursquare datasets, which demonstrate the improvement our model achieves on semantic coherence. We further apply the learned embeddings to two downstream applications, namely next point-of-interest recommendation and trajectory verification. Empirical results demonstrate the advantages of the disentangled embeddings over four state-of-the-art unsupervised location embedding methods.

We consider the problem of Human-Object Interaction (HOI) Detection, which aims to locate and recognize HOI instances in the form of in images. Most existing works treat HOIs as individual interaction categories, thus can not handle the problem of long-tail distribution and polysemy of action labels. We argue that multi-level consistencies among objects, actions and interactions are strong cues for generating semantic representations of rare or previously unseen HOIs. Leveraging the compositional and relational peculiarities of HOI labels, we propose ConsNet, a knowledge-aware framework that explicitly encodes the relations among objects, actions and interactions into an undirected graph called consistency graph, and exploits Graph Attention Networks (GATs) to propagate knowledge among HOI categories as well as their constituents. Our model takes visual features of candidate human-object pairs and word embeddings of HOI labels as inputs, maps them into visual-semantic joint embedding space and obtains detection results by measuring their similarities. We extensively evaluate our model on the challenging V-COCO and HICO-DET datasets, and results validate that our approach outperforms state-of-the-arts under both fully-supervised and zero-shot settings.

Sequential recommendation is one of the main tasks in recommender systems, where the next action (e.g., purchase, visit, and click) of the user is predicted based on his/her past sequence of actions. Translating Embeddings is a knowledge graph completion approach which was recently adapted to a translation-based sequential recommendation (TransRec) method. We observe a flaw of TransRec when handling complex translations, which hinders it from generating accurate suggestions. In view of this, we propose a translation-based recommender for complex users (CTransRec), which utilizes category-specific projection and temporal dynamic relaxation. Using our proposed Margin-based Pairwise Bayesian Personalized Ranking and Time-Aware Negative Sampling, CTransRec outperforms state-of-the-art methods for sequential recommendation on extremely sparse data. The superiority of CTransRec, which is confirmed by our extensive experiments on both public data and real data obtained from the industry, comes from not only the additional information used in training but also the fact that CTransRec makes good use of this additional information to model the complex translations.

We present Mmkg, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs. Therefore, multi-relational link prediction and entity matching communities can benefit from this resource. We believe this data set has the potential to facilitate the development of novel multi-modal learning approaches for knowledge graphs. We validate the utility of Mmkg in the $$\mathtt {sameAs}$$ link prediction task with an extensive set of experiments. These experiments show that the task at hand benefits from learning of multiple feature types.

This paper tackles the problem of providing users with ranked lists of relevant search results, by incorporating contextual features of the users and search results, and learning how a user values multiple objectives. For example, to recommend a ranked list of hotels, an algorithm must learn which hotels are the right price for users, as well as how users vary in their weighting of price against the location. In our paper, we formulate the context-aware, multi-objective, ranking problem as a Multi-Objective Contextual Ranked Bandit (MOCR-B). To solve the MOCR-B problem, we present a novel algorithm, named Multi-Objective Utility-Upper Confidence Bound (MOU-UCB). The goal of MOU-UCB is to learn how to generate a ranked list of resources that maximizes the rewards in multiple objectives to give relevant search results. Our algorithm learns to predict rewards in multiple objectives based on contextual information (combining the Upper Confidence Bound algorithm for multi-armed contextual bandits with neural network embeddings), as well as learns how a user weights the multiple objectives. Our empirical results reveal that the ranked lists generated by MOU-UCB lead to better click-through rates, compared to approaches that do not learn the utility function over multiple reward objectives.

Urban flow monitoring systems play important roles in smart city efforts around the world. However, the ubiquitous deployment of monitoring devices, such as CCTVs, induces a long-lasting and enormous cost for maintenance and operation. This suggests the need for a technology that can reduce the number of deployed devices, while preventing the degeneration of data accuracy and granularity. In this paper, we aim to infer the real-time and fine-grained crowd flows throughout a city based on coarse-grained observations. This task is challenging due to the two essential reasons: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a method entitled UrbanFM based on deep neural networks. Our model consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs by using a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influences of different external factors. Extensive experiments on two real-world datasets validate the effectiveness and efficiency of our method, demonstrating its state-of-the-art performance on this problem.

Automatic political preference prediction from social media posts has to date proven successful only in distinguishing between publicly declared liberals and conservatives in the US.This study examines users' political ideology using a sevenpoint scale which enables us to identify politically moderate and neutral usersgroups which are of particular interest to political scientists and pollsters.Using a novel data set with political ideology labels self-reported through surveys, our goal is two-fold: a) to characterize the political groups of users through language use on Twitter; b) to build a fine-grained model that predicts political ideology of unseen users.Our results identify differences in both political leaning and engagement and the extent to which each group tweets using political keywords.Finally, we demonstrate how to improve ideology prediction accuracy by exploiting the relationships between the user groups.

A key challenge in complex activity recognition is the fact that a complex activity can often be performed in several different ways, with each consisting of its own configuration of atomic actions and their temporal dependencies. This leads us to define an atomic activity-based probabilistic framework that employs Allen's interval relations to represent local temporal dependencies. The framework introduces a latent variable from the Chinese Restaurant Process to explicitly characterize these unique internal configurations of a particular complex activity as a variable number of tables.It can be analytically shown that the resulting interval network satisfies the transitivity property, and as a result, all local temporal dependencies can be retained and are globally consistent.Empirical evaluations on benchmark datasets suggest our approach significantly outperforms the state-of-the-art methods.

People go to fortune tellers in hopes of learning things about their future. A future career path is one of the topics most frequently discussed. But rather than rely on "black arts" to make predictions, in this work we scientifically and systematically study the feasibility of career path prediction from social network data. In particular, we seamlessly fuse information from multiple social networks to comprehensively describe a user and characterize progressive properties of his or her career path. This is accomplished via a multi-source learning framework with fused lasso penalty, which jointly regularizes the source and career-stage relatedness. Extensive experiments on real-world data confirm the accuracy of our model.

Tracking generic human motion is highly challenging due to its high-dimensional state space and the various motion types involved. In order to deal with these challenges, a fusion formulation which integrates low- and high-dimensional tracking approaches into one framework is proposed. The low-dimensional approach successfully overcomes the high-dimensional problem of tracking the motions with available training data by learning motion models, but it only works with specific motion types. On the other hand, although the high-dimensional approach may recover the motions without learned models by sampling directly in the pose space, it lacks robustness and efficiency. Within the framework, the two parallel approaches, low- and high-dimensional, are fused via a probabilistic approach at each time step. This probabilistic fusion approach ensures that the overall performance of the system is improved by concentrating on the respective advantages of the two approaches and resolving their weak points. The experimental results, after qualitative and quantitative comparisons, demonstrate the effectiveness of the proposed approach in tracking generic human motion.