The rapid advancements in Large Vision Models (LVMs), such as Vision Transformers (ViTs), diffusion models, and visual autoregressive models, have led to an increasing demand for computational resources, resulting in substantial financial and environmental costs. This growing challenge highlights the necessity of developing efficient training methods for LVMs. Progressive learning, a training strategy in which model capacity gradually increases during training, has shown promise in addressing these challenges. In this paper, we take a practical step toward the efficient training of LVMs by automating progressive learning. We focus first on the pre-training of LVMs, using ViTs as a case study. We propose AutoProg-One, an automated progressive learning scheme featuring momentum growth (MoGrow) and the one-shot growth schedule search. Additionally, we extend our approach beyond pre-training to address the transfer learning and fine-tuning of LVMs. We also expand the scope of AutoProg to encompass a wider range of LVMs, including diffusion models and visual autoregressive model. First, we introduce AutoProg-Zero, by enhancing the AutoProg framework with a novel zero-shot automated progressive learning method, eliminating the need for one-shot supernet training. Second, we introduce a novel Unique Stage Identifier (SID) scheme to bridge the gap during network growth. These innovations, integrated with the core principles of AutoProg, offer a comprehensive solution for efficient training across various LVM scenarios. Extensive experiments show that AutoProg accelerates ViT pre-training by up to 1.85 ×on ImageNet and accelerates the fine-tuning of diffusion models, and visual autoregressive model by up to 2.86 × and 1.89 ×, with comparable or even better performance. This work provides a robust and scalable approach to efficient training of LVMs, with potential applications in a wide range of vision tasks.

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely on annotated 3D datasets and predefined object categories, limiting scalability and adaptability. To overcome these limitations, we introduce SeeGround, a zero-shot 3DVG framework leveraging 2D Vision-Language Models (VLMs) trained on large-scale 2D data. SeeGround represents 3D scenes as a hybrid of query-aligned rendered images and spatially enriched text descriptions, bridging the gap between 3D data and 2D-VLMs input formats. We propose two modules: the Perspective Adaptation Module, which dynamically selects viewpoints for query-relevant image rendering, and the Fusion Alignment Module, which integrates 2D images with 3D spatial descriptions to enhance object localization. Extensive experiments on ScanRefer and Nr3D demonstrate that our approach outperforms existing zero-shot methods by large margins. Notably, we exceed weakly supervised methods and rival some fully supervised ones, outperforming previous SOTA by 7.7% on ScanRefer and 7.1% on Nr3D, showcasing its effectiveness in complex 3DVG tasks. Project website (with demo and code): https://seeground.github.io.

Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a significant challenge. Recent research has explored leveraging large-scale human activity data for pre-training, but the substantial morphological differences between humans and robots introduce a significant human-robot domain discrepancy, hindering the generalization of these models to downstream manipulation tasks. To overcome this, we propose a novel adaptation paradigm that leverages readily available paired human-robot video data to bridge the domain gap. Our method employs a human-robot contrastive alignment loss to align the semantics of human and robot videos, adapting pre-trained models to the robot domain in a parameter-efficient manner. Experiments on 20 simulated tasks across two different benchmarks and five real-world tasks demonstrate significant improvements. These results span both single-task and language-conditioned multi-task settings, evaluated using two different pre-trained models. Compared to existing pre-trained models, our adaptation method improves the average success rate by over 7% across multiple tasks on both simulated benchmarks and real-world evaluations. Project: https://jiaming-zhou.github.io/projects/HumanRobotAlign

Estimating physical properties for visual data is a crucial task in computer vision, graphics, and robotics, underpinning applications such as augmented reality, physical simulation, and robotic grasping. However, this area remains under-explored due to the inherent ambiguities in physical property estimation. To address these challenges, we introduce GaussianProperty, a training-free framework that assigns physical properties of materials to 3D Gaussians. Specifically, we integrate the segmentation capability of SAM with the recognition capability of GPT-4V(ision) to formulate a global-local physical property reasoning module for 2D images. Then we project the physical properties from multi-view 2D images to 3D Gaussians using a voting strategy. We demonstrate that 3D Gaussians with physical property annotations enable applications in physics-based dynamic simulation and robotic grasping. For physics-based dynamic simulation, we leverage the Material Point Method (MPM) for realistic dynamic simulation. For robot grasping, we develop a grasping force prediction strategy that estimates a safe force range required for object grasping based on the estimated physical properties. Extensive experiments on material segmentation, physics-based dynamic simulation, and robotic grasping validate the effectiveness of our proposed method, highlighting its crucial role in understanding physical properties from visual data. Online demo, code, more cases and annotated datasets are available on \href{https://Gaussian-Property.github.io}{this https URL}.

To navigate safely and efficiently in crowded spaces, robots should not only perceive the current state of the environment but also anticipate future human movements. In this paper, we propose a reinforcement learning architecture, namely Falcon, to tackle socially-aware navigation by explicitly predicting human trajectories and penalizing actions that block future human paths. To facilitate realistic evaluation, we introduce a novel SocialNav benchmark containing two new datasets, Social-HM3D and Social-MP3D. This benchmark offers large-scale photo-realistic indoor scenes populated with a reasonable amount of human agents based on scene area size, incorporating natural human movements and trajectory patterns. We conduct a detailed experimental analysis with the state-of-the-art learning-based method and two classic rulebased path-planning algorithms on the new benchmark. The results demonstrate the importance of future prediction and our method achieves the best task success rate of 55% while maintaining about 90% personal space compliance. We will release our code and datasets.

Meteorological heatmaps play a vital role in deciphering extreme weather phenomena, yet their inherent complexities-marked by irregular contours, unstructured patterns, and complex color variations-present unique analytical hurdles for state-of-the-art Vision-Language Models (VLMs). Current state-of-the-art models like GPT-4o, Qwen-VL, and LLaVA 1.6 struggle with tasks such as precise color identification and spatial localization, resulting in inaccurate or incomplete interpretations. To address these challenges, we introduce Sparse Position and Outline Tracking (SPOT), a novel algorithm specifically designed to process irregularly shaped colored regions in visual data. SPOT identifies and localizes these regions by extracting their spatial coordinates, enabling structured representations of irregular shapes. Building on SPOT, we construct ClimateIQA, a novel meteorological visual question answering (VQA) dataset, comprising 26,280 high-resolution heatmaps and 762,120 instruction samples for wind gust, total precipitation, wind chill index and heat index analysis. ClimateIQA enhances VLM training by incorporating spatial cues, geographic metadata, and reanalysis data, improving model accuracy in interpreting and describing extreme weather features. Furthermore, we develop Climate-Zoo, a suite of fine-tuned VLMs based on SPOT-empowered ClimateIQA, which significantly outperforms existing models in meteorological heatmap tasks.

Visual grounding in 3D is the key for embodied agents to localize language-referred objects in open-world environments. However, existing benchmarks are limited to indoor focus, single-platform constraints, and small scale. We introduce 3EED, a multi-platform, multi-modal 3D grounding benchmark featuring RGB and LiDAR data from vehicle, drone, and quadruped platforms. We provide over 128,000 objects and 22,000 validated referring expressions across diverse outdoor scenes -- 10x larger than existing datasets. We develop a scalable annotation pipeline combining vision-language model prompting with human verification to ensure high-quality spatial grounding. To support cross-platform learning, we propose platform-aware normalization and cross-modal alignment techniques, and establish benchmark protocols for in-domain and cross-platform evaluations. Our findings reveal significant performance gaps, highlighting the challenges and opportunities of generalizable 3D grounding. The 3EED dataset and benchmark toolkit are released to advance future research in language-driven 3D embodied perception.

The generalization capabilities of vision-language-action (VLA) models to unseen tasks are crucial to achieving general-purpose robotic manipulation in open-world settings. However, the cross-task generalization capabilities of existing VLA models remain significantly underexplored. To address this gap, we introduce **AGNOSTOS**, a novel simulation benchmark designed to rigorously evaluate cross-task zero-shot generalization in manipulation. AGNOSTOS comprises 23 unseen manipulation tasks for test—distinct from common training task distributions—and incorporates two levels of generalization difficulty to assess robustness. Our systematic evaluation reveals that current VLA models, despite being trained on diverse datasets, struggle to generalize effectively to these unseen tasks. To overcome this limitation, we propose **Cross-Task In-Context Manipulation (X-ICM)**, a method that conditions large language models (LLMs) on in-context demonstrations from seen tasks to predict action sequences for unseen tasks. Additionally, we introduce a **dynamics-guided sample selection** strategy that identifies relevant demonstrations by capturing cross-task dynamics. On AGNOSTOS, X-ICM significantly improves cross-task zero-shot generalization performance over leading VLAs, achieving improvements of 6.0\% over $\pi_0$ and 7.9\% over VoxPoser. We believe AGNOSTOS and X-ICM will serve as valuable tools for advancing general-purpose robotic manipulation.

Jian Chen, Peilin Zhou, Yining Hua, Loh Xin, Kehui Chen, Ziyuan Li, Bing Zhu, Junwei Liang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Evaluating and training autonomous driving systems require diverse and scalable corner cases. However, most existing scene generation methods lack controllability, accuracy, and versatility, resulting in unsatisfactory generation results. Inspired by DragGAN in image generation, we propose DragTraffic, a generalized, interactive, and controllable traffic scene generation framework based on conditional diffusion. DragTraffic enables non-experts to generate a variety of realistic driving scenarios for different types of traffic agents through an adaptive mixture expert architecture. We employ a regression model to provide a general initial solution and a refinement process based on the conditional diffusion model to ensure diversity. User-customized context is introduced through cross-attention to ensure high controllability. Experiments on a real-world driving dataset show that DragTraffic outperforms existing methods in terms of authenticity, diversity, and freedom. Demo videos and code are available at https://chantsss.github.io/Dragtraffic/.

Teli Ma, Rong Li, Junwei Liang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Gloss-free sign language translation (SLT) aims to develop well-performing SLT systems with no requirement for the costly gloss annotations, but currently still lags behind gloss-based approaches significantly. In this paper, we identify **a representation density problem** that could be a bottleneck in restricting the performance of gloss-free SLT. Specifically, the representation density problem describes that the visual representations of semantically distinct sign gestures tend to be closely packed together in feature space, which makes gloss-free methods struggle with distinguishing different sign gestures and suffer from a sharp performance drop. To address the representation density problem, we introduce a simple but effective contrastive learning strategy, namely SignCL, which encourages gloss-free models to learn more discriminative feature representation in a self-supervised manner. Our experiments demonstrate that the proposed SignCL can significantly reduce the representation density and improve performance across various translation frameworks. Specifically, SignCLachieves a significant improvement in BLEU score for the Sign Language Transformer and GFSLT-VLP on the CSL-Daily dataset by 39\% and 46\%, respectively, without any increase of model parameters. Compared to Sign2GPT, a state-of-the-art method based on large-scale pre-trained vision and language models, SignCLachieves better performance with only 35\% of its parameters. We will release our code and model to facilitate further research.

We study the problem of human action recognition using motion capture (MoCap) sequences. Unlike existing techniques that take multiple manual steps to derive standard-ized skeleton representations as model input, we propose a novel Spatial-Temporal Mesh Transformer (STMT) to directly model the mesh sequences. The model uses a hierarchical transformer with intra-frame off-set attention and inter-frame self-attention. The attention mechanism allows the model to freely attend between any two vertex patches to learn nonlocal relationships in the spatial-temporal domain. Masked vertex modeling and future frame prediction are used as two self-supervised tasks to fully activate the bi-directional and auto-regressive attention in our hierarchical transformer. The proposed method achieves state-of-the-art performance compared to skeleton-based and point-cloud-based models on common MoCap benchmarks. Code is available at https://github.com/zgzxy001/STMT.

We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action recognition in the past decade, it remains challenging yet valuable how to train a single model that can perform well across multiple datasets. Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss, aiming tolearn robust representations for action recognition. In particular, the informative loss maximizes the expressiveness of the feature embedding while the projection loss for each dataset mines the intrinsic relations between classes across datasets. We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2 datasets. Extensive experimental results show that our method can consistently improve state-of-the-art performance. Code and models are released.

Cross-modal retrieval between videos and texts has gained increasing interest because of the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part of the information. Thus, a video can have multiple different text descriptions and queries. We call it the Video-Text Correspondence Ambiguity problem. Current techniques mostly concentrate on mining local or multi-level alignment between contents of video and text (e.g., object to entity and action to verb). It is difficult for these methods to alleviate video-text correspondence ambiguity by describing a video using only one feature, which is required to be matched with multiple different text features at the same time. To address this problem, we propose a Text-Adaptive Multiple Visual Prototype Matching Model. It automatically captures multiple prototypes to describe a video by adaptive aggregation on video token features. Given a query text, the similarity is determined by the most similar prototype to find correspondence in the video, which is called text-adaptive matching. To learn diverse prototypes for representing the rich information in videos, we propose a variance loss to encourage different prototypes to attend to different contents of the video. Our method outperforms the state-of-the-art methods on four public video retrieval datasets.

We propose a novel weakly supervised approach for 3D semantic segmentation on volumetric images. Unlike most existing methods that require voxel-wise densely labeled training data, our weakly-supervised CIVA-Net is the first model that only needs image-level class labels as guidance to learn accurate volumetric segmentation. Our model learns from cross-image co-occurrence for integral region generation, and explores inter-voxel affinity relations to predict segmentation with accurate boundaries. We empirically validate our model on both simulated and real cryo-ET datasets. Our experiments show that CIVA-Net achieves comparable performance to the state-of-the-art models trained with stronger supervision.

In this paper, we study the problem of efficiently assessing building damage after natural disasters like hurricanes, floods or fires, through aerial video analysis. We make two main contributions. The first contribution is a new dataset, consisting of user-generated aerial videos from social media with annotations of instance-level building damage masks. This provides the first benchmark for quantitative evaluation of models to assess building damage using aerial videos. The second contribution is a new model, namely MSNet, which contains novel region proposal network designs and an unsupervised score refinement network for confidence score calibration in both bounding box and mask branches. We show that our model achieves state-of-the-art results compared to previous methods in our dataset.

This paper studies the problem of predicting the distribution over multiple possible future paths of people as they move through various visual scenes. We make two main contributions. The first contribution is a new dataset, created in a realistic 3D simulator, which is based on real world trajectory data, and then extrapolated by human annotators to achieve different latent goals. This provides the first benchmark for quantitative evaluation of the models to predict multi-future trajectories. The second contribution is a new model to generate multiple plausible future trajectories, which contains novel designs of using multi-scale location encodings and convolutional RNNs over graphs. We refer to our model as Multiverse. We show that our model achieves the best results on our dataset, as well as on the real-world VIRAT/ActEV dataset (which just contains one possible future).

Nowadays a huge number of user-generated videos are uploaded to social media every second, capturing glimpses of events all over the world. These videos in the wild provide important and useful information for reconstructing events like the Las Vegas Shooting in 2017. In this paper, we describe a system that can localize the shooter location only based on a couple of user-generated videos that capture the gunshot sound. Our system first utilizes established video analysis techniques like video synchronization and automatic gunshot processing to organize the unstructured videos in the wild for users to understand the event effectively. By combining multimodal information from visual, audio and geo-locations, our system can then visualize all possible locations of the shooter in the map. Our system provides a web interface for human-in-the-loop verification to ensure accurate estimations. We present the results of estimating the shooter's location of the Las Vegas Shooting in 2017 and show that our system is able to get accurate location using only the first few gunshots. All relevant source code including the web interface and machine learning models are available.

Deciphering human behaviors to predict their future paths/trajectories and what they would do from videos is important in many applications. Motivated by this idea, this paper studies predicting a pedestrian's future path jointly with future activities. We propose an end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings. To facilitate the training, the network is learned with an auxiliary task of predicting future location in which the activity will happen. Experimental results demonstrate our state-of-the-art performance over two public benchmarks on future trajectory prediction. Moreover, our method is able to produce meaningful future activity prediction in addition to the path. The result provides the first empirical evidence that joint modeling of paths and activities benefits future path prediction.

Nowadays a huge number of user-generated videos are uploaded to social media every second, capturing glimpses of events all over the world. These videos provide important and useful information for reconstructing events like the Las Vegas Shooting in 2017. In this paper, we describe a system that can localize the shooter location only based on a couple of user-generated videos that capture the gunshot sound. Our system first utilizes established video analysis techniques like video synchronization and gunshot temporal localization to organize the unstructured social media videos for users to understand the event effectively. By combining multimodal information from visual, audio and geo-locations, our system can then visualize all possible locations of the shooter in the map. Our system provides a web interface for human-in-the-loop verification to ensure accurate estimations. We present the results of estimating the shooter's location of the Las Vegas Shooting in 2017 and show that our system is able to get accurate location using only the first few gunshots. The full technical report, all relevant source code including the web interface and machine learning models are available.

Recent insights on language and vision with neural networks have been successfully applied to simple single-image visual question answering. However, to tackle real-life question answering problems on multimedia collections such as personal photo albums, we have to look at whole collections with sequences of photos. This paper proposes a new multimodal MemexQA task: given a sequence of photos from a user, the goal is to automatically answer questions that help users recover their memory about an event captured in these photos. In addition to a text answer, a few grounding photos are also given to justify the answer. The grounding photos are necessary as they help users quickly verifying the answer. Towards solving the task, we 1) present the MemexQA dataset, the first publicly available multimodal question answering dataset consisting of real personal photo albums; 2) propose an end-to-end trainable network that makes use of a hierarchical process to dynamically determine what media and what time to focus on in the sequential data to answer the question. Experimental results on the MemexQA dataset demonstrate that our model outperforms strong baselines and yields the most relevant grounding photos on this challenging task.

Recent insights on language and vision with neural networks have been successfully applied to simple single-image visual question answering. However, to tackle real-life question answering problems on multimedia collections such as personal photos, we have to look at whole collections with sequences of photos or videos. When answering questions from a large collection, a natural problem is to identify snippets to support the answer. In this paper, we describe a novel neural network called Focal Visual-Text Attention network (FVTA) for collective reasoning in visual question answering, where both visual and text sequence information such as images and text metadata are presented. FVTA introduces an end-to-end approach that makes use of a hierarchical process to dynamically determine what media and what time to focus on in the sequential data to answer the question. FVTA can not only answer the questions well but also provides the justifications which the system results are based upon to get the answers. FVTA achieves state-of-the-art performance on the MemexQA dataset and competitive results on the MovieQA dataset.

Developing an efficient and effective social media monitoring system has become one of the important steps towards improved public safety. With the explosive availability of user-generated content documenting most conflicts and human rights abuses around the world, analysts and first-responders increasingly find themselves overwhelmed with massive amounts of noisy data from social media. In this paper, we construct a large-scale public safety event dataset with retrospective automatic labeling for 4.2 million multimodal tweets from 7 public safety events occurred in 2013~2017. We propose a new multimodal social media filtering system composed of encoding, classification, and correlation networks to jointly learn shared and complementary visual and textual information to filter out the most relevant and useful items among the noisy social media influx. The proposed model is verified and achieves significant improvement over competitive baselines under the retrospective and real-time experimental protocols.

What happened during the Boston Marathon in 2013? Nowadays, at any major event, lots of people take videos and share them on social media. To fully understand exactly what happened in these major events, researchers and analysts often have to examine thousands of these videos manually. To reduce this manual effort, we present an investigative system that automatically synchronizes these videos to a global timeline and localizes them on a map. In addition to alignment in time and space, our system combines various functions for analysis, including gunshot detection, crowd size estimation, 3D reconstruction and person tracking. To our best knowledge, this is the first time a unified framework has been built for comprehensive event reconstruction for social media videos.

Given any complicated or specialized video content search query, e.g. ”Batkid (a kid in batman costume)” or ”destroyed buildings”, existing methods require manually labeled data to build detectors for searching. We present a demonstration of an artificial intelligence application, Webly-labeled Learning (WELL) that enables learning of ad-hoc concept detectors over unlimited Internet videos without any manual an-notations. A considerable number of videos on the web are associated with rich but noisy contextual information, such as the title, which provides a type of weak annotations or la-bels of the video content. To leverage this information, our system employs state-of-the-art webly-supervised learning(WELL) (Liang et al. ). WELL considers multi-modal information including deep learning visual, audio and speech features, to automatically learn accurate video detectors based on the user query. The learned detectors from a large number of web videos allow users to search relevant videos over their personal video archives, not requiring any textual metadata,but as convenient as searching on Youtube.

In the era of social media, a large number of user-generated videos are uploaded to the Internet every day, capturing events all over the world. Reconstructing the event truth based on information mined from these videos has been an emerging challenging task. Temporal alignment of videos “in the wild” which capture different moments at different positions with different perspectives is the critical step. In this paper, we propose a hierarchical approach to synchronize videos. Our system utilizes clustered audio-signatures to align video pairs. Global alignment for all videos is then achieved via forming alignable video groups with self-paced learning. Experiments on the Boston Marathon dataset show that the proposed method achieves excellent precision and robustness.

With the explosion in the availability of user-generated videos documenting any conflicts and human rights abuses around the world, analysts and researchers increasingly find themselves overwhelmed with massive amounts of video data to acquire and analyze useful information. In this paper, we develop a temporal localization framework for intense audio events in videos which addresses the problem. The proposed method utilizes Localized Self-Paced Reranking (LSPaR) to refine the localization results. LSPaR utilizes samples from easy to noisier ones so that it can overcome the noisiness of the initial retrieval results from user-generated videos. We show our framework's efficacy on localizing intense audio event like gunshot, and further experiments also indicate that our methods can be generalized to localizing other audio events in noisy videos.

Learning video concept detectors automatically from the big but noisy web data with no additional manual annotations is a novel but challenging area in the multimedia and the machine learning community. A considerable amount of videos on the web is associated with rich but noisy contextual information, such as the title and other multi-modal information, which provides weak annotations or labels about the video content. To tackle the problem of large-scale noisy learning, We propose a novel method called Multi-modal WEbly-Labeled Learning (WELL-MM), which is established on the state-of-the-art machine learning algorithm inspired by the learning process of human. WELL-MM introduces a novel multi-modal approach to incorporate meaningful prior knowledge called curriculum from the noisy web videos. We empirically study the curriculum constructed from the multi-modal features of the Internet videos and images. The comprehensive experimental results on FCVID and YFCC100M demonstrate that WELL-MM outperforms state-of-the-art studies by a statically significant margin on learning concepts from noisy web video data. In addition, the results also verify that WELL-MM is robust to the level of noisiness in the video data. Notably, WELL-MM trained on sufficient noisy web labels is able to achieve a better accuracy to supervised learning methods trained on the clean manually labeled data.

The recent advances in image captioning stimulate the research in generating natural language description for visual content, which can be widely applied in many applications such as assisting blind people. Video description generation is a more complex task than image caption. Most works of video description generation focus on visual information in the video. However, audio provides rich information for describing video contents as well. In this paper, we propose to generate video descriptions in natural sentences using both audio and visual cues. We use unified deep neural networks with both convolutional and recurrent structure. Experimental results on the Microsoft Research Video Description (MSVD) corpus prove that fusing audio information greatly improves the video description performance.

With the increasing use of audio sensors in user generated content collection, how to detect semantic concepts using audio streams has become an important research problem. In this paper, we present a semantic concept annotation system using soundtracks/ audio of the video. We investigate three different acoustic feature representations for audio semantic concept annotation and explore fusion of audio annotation with visual annotation systems. We test our system on the data collection from HUAWEI Accurate and Fast Mobile Video Annotation Grand Challenge 2014. The experimental results show that our audio-only concept annotation system can detect semantic concepts significantly better than random guess. It can also provide significant complementary information to the visual-based concept annotation system for performance boost. Further detailed analysis shows that for interpreting a semantic concept both visually and acoustically, it is better to train concept models for the visual system and audio system using visual-driven and audio-driven ground truth separately.

With the increasing use of audio sensors in user generated content (UGC) collections, semantic concept annotation from video soundtracks has become an important research problem. In this paper, we investigate reducing the semantic gap of the traditional data-driven bag-of-audio-words based audio annotation approach by utilizing the large-amount of wild audio data and their rich user tags, from which we propose a new feature representation based on semantic class model distance. We conduct experiments on the data collection from HUAWEI Accurate and Fast Mobile Video Annotation Grand Challenge 2014. We also fuse the audio-only annotation system with a visual-only system. The experimental results show that our audio-only concept annotation system can detect semantic concepts significantly better than does random guessing. The new feature representation achieves comparable annotation performance with the bag-of-audio-words feature. In addition, it can provide more semantic interpretation in the output. The experimental results also prove that the audio-only system can provide significant complementary information to the visual-only concept annotation system for performance boost and for better interpretation of semantic concepts both visually and acoustically.