Alexander Hauptmann

Xiaoyu Zhu, Po-Yao Huang, Junwei Liang et al. · meta-ai

We study the problem of human action recognition using motion capture (MoCap) sequences. Unlike existing techniques that take multiple manual steps to derive standardized 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 non-local 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.

Changdae Oh, Hyesu Lim, Mijoo Kim et al. · cmu, uw

Improving out-of-distribution (OOD) generalization during in-distribution (ID) adaptation is a primary goal of robust fine-tuning of zero-shot models beyond naive fine-tuning. However, despite decent OOD generalization performance from recent robust fine-tuning methods, confidence calibration for reliable model output has not been fully addressed. This work proposes a robust fine-tuning method that improves both OOD accuracy and confidence calibration simultaneously in vision language models. Firstly, we show that both OOD classification and OOD calibration errors have a shared upper bound consisting of two terms of ID data: 1) ID calibration error and 2) the smallest singular value of the ID input covariance matrix. Based on this insight, we design a novel framework that conducts fine-tuning with a constrained multimodal contrastive loss enforcing a larger smallest singular value, which is further guided by the self-distillation of a moving-averaged model to achieve calibrated prediction as well. Starting from empirical evidence supporting our theoretical statements, we provide extensive experimental results on ImageNet distribution shift benchmarks that demonstrate the effectiveness of our theorem and its practical implementation.

Xiaoyu Zhu, Hao Zhou, Pengfei Xing et al. · deepmind

In this paper, we investigate the use of diffusion models which are pre-trained on large-scale image-caption pairs for open-vocabulary 3D semantic understanding. We propose a novel method, namely Diff2Scene, which leverages frozen representations from text-image generative models, along with salient-aware and geometric-aware masks, for open-vocabulary 3D semantic segmentation and visual grounding tasks. Diff2Scene gets rid of any labeled 3D data and effectively identifies objects, appearances, materials, locations and their compositions in 3D scenes. We show that it outperforms competitive baselines and achieves significant improvements over state-of-the-art methods. In particular, Diff2Scene improves the state-of-the-art method on ScanNet200 by 12%.

Haoyang Wen, Honglei Zhuang, Hamed Zamani et al. · deepmind

Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking quality of knowledge candidates for answer generation. Our reranking module takes multi-modal information from both candidates and questions and performs cross-item interaction for better relevance score modeling. Experiments on OK-VQA and A-OKVQA show that multi-modal reranker from distant supervision provides consistent improvements. We also find a training-testing discrepancy with reranking in answer generation, where performance improves if training knowledge candidates are similar to or noisier than those used in testing.

Gabriel Moreira, Manuel Marques, João Paulo Costeira et al.

Recent research in representation learning has shown that hierarchical data lends itself to low-dimensional and highly informative representations in hyperbolic space. However, even if hyperbolic embeddings have gathered attention in image recognition, their optimization is prone to numerical hurdles. Further, it remains unclear which applications stand to benefit the most from the implicit bias imposed by hyperbolicity, when compared to traditional Euclidean features. In this paper, we focus on prototypical hyperbolic neural networks. In particular, the tendency of hyperbolic embeddings to converge to the boundary of the Poincaré ball in high dimensions and the effect this has on few-shot classification. We show that the best few-shot results are attained for hyperbolic embeddings at a common hyperbolic radius. In contrast to prior benchmark results, we demonstrate that better performance can be achieved by a fixed-radius encoder equipped with the Euclidean metric, regardless of the embedding dimension.

Kai Wang, Zekai Li, Zhi-Qi Cheng et al.

Dataset distillation has demonstrated strong performance on simple datasets like CIFAR, MNIST, and TinyImageNet but struggles to achieve similar results in more complex scenarios. In this paper, we propose EDF (emphasizes the discriminative features), a dataset distillation method that enhances key discriminative regions in synthetic images using Grad-CAM activation maps. Our approach is inspired by a key observation: in simple datasets, high-activation areas typically occupy most of the image, whereas in complex scenarios, the size of these areas is much smaller. Unlike previous methods that treat all pixels equally when synthesizing images, EDF uses Grad-CAM activation maps to enhance high-activation areas. From a supervision perspective, we downplay supervision signals that have lower losses, as they contain common patterns. Additionally, to help the DD community better explore complex scenarios, we build the Complex Dataset Distillation (Comp-DD) benchmark by meticulously selecting sixteen subsets, eight easy and eight hard, from ImageNet-1K. In particular, EDF consistently outperforms SOTA results in complex scenarios, such as ImageNet-1K subsets. Hopefully, more researchers will be inspired and encouraged to improve the practicality and efficacy of DD. Our code and benchmark will be made public at https://github.com/NUS-HPC-AI-Lab/EDF.

Chao Xu, Mingze Sun, Zhi-Qi Cheng et al.

In this paper, we propose a novel framework, Combo, for harmonious co-speech holistic 3D human motion generation and efficient customizable adaption. In particular, we identify that one fundamental challenge as the multiple-input-multiple-output (MIMO) nature of the generative model of interest. More concretely, on the input end, the model typically consumes both speech signals and character guidance (e.g., identity and emotion), which not only poses challenge on learning capacity but also hinders further adaptation to varying guidance; on the output end, holistic human motions mainly consist of facial expressions and body movements, which are inherently correlated but non-trivial to coordinate in current data-driven generation process. In response to the above challenge, we propose tailored designs to both ends. For the former, we propose to pre-train on data regarding a fixed identity with neutral emotion, and defer the incorporation of customizable conditions (identity and emotion) to fine-tuning stage, which is boosted by our novel X-Adapter for parameter-efficient fine-tuning. For the latter, we propose a simple yet effective transformer design, DU-Trans, which first divides into two branches to learn individual features of face expression and body movements, and then unites those to learn a joint bi-directional distribution and directly predicts combined coefficients. Evaluated on BEAT2 and SHOW datasets, Combo is highly effective in generating high-quality motions but also efficient in transferring identity and emotion. Project website: \href{https://xc-csc101.github.io/combo/}{Combo}.

Ruohong Zhang, Liangke Gui, Zhiqing Sun et al. · cmu

Preference modeling techniques, such as direct preference optimization (DPO), has shown effective in enhancing the generalization abilities of large language model (LLM). However, in tasks involving video instruction-following, providing informative feedback, especially for detecting hallucinations in generated responses, remains a significant challenge. Previous studies have explored using large large multimodal models (LMMs) as reward models to guide preference modeling, but their ability to accurately assess the factuality of generated responses compared to corresponding videos has not been conclusively established. This paper introduces a novel framework that utilizes detailed video captions as a proxy of video content, enabling language models to incorporate this information as supporting evidence for scoring video Question Answering (QA) predictions. Our approach demonstrates robust alignment with OpenAI GPT-4V model's reward mechanism, which directly takes video frames as input. Furthermore, we show that applying this tailored reward through DPO significantly improves the performance of video LMMs on video QA tasks.

Po-Yao Huang, Mandela Patrick, Junjie Hu et al.

This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings. Under a zero-shot setting, we empirically demonstrate that performance degrades significantly when we query the multilingual text-video model with non-English sentences. To address this problem, we introduce a multilingual multimodal pre-training strategy, and collect a new multilingual instructional video dataset (MultiHowTo100M) for pre-training. Experiments on VTT show that our method significantly improves video search in non-English languages without additional annotations. Furthermore, when multilingual annotations are available, our method outperforms recent baselines by a large margin in multilingual text-to-video search on VTT and VATEX; as well as in multilingual text-to-image search on Multi30K. Our model and Multi-HowTo100M is available at http://github.com/berniebear/Multi-HT100M.

Seokeon Choi, Junhyun Lee, Yunsung Lee et al.

We propose an improved discriminative model prediction method for robust long-term tracking based on a pre-trained short-term tracker. The baseline pre-trained short-term tracker is SuperDiMP which combines the bounding-box regressor of PrDiMP with the standard DiMP classifier. Our tracker RLT-DiMP improves SuperDiMP in the following three aspects: (1) Uncertainty reduction using random erasing: To make our model robust, we exploit an agreement from multiple images after erasing random small rectangular areas as a certainty. And then, we correct the tracking state of our model accordingly. (2) Random search with spatio-temporal constraints: we propose a robust random search method with a score penalty applied to prevent the problem of sudden detection at a distance. (3) Background augmentation for more discriminative feature learning: We augment various backgrounds that are not included in the search area to train a more robust model in the background clutter. In experiments on the VOT-LT2020 benchmark dataset, the proposed method achieves comparable performance to the state-of-the-art long-term trackers. The source code is available at: https://github.com/bismex/RLT-DIMP.

Gabriel Moreira, Manuel Marques, João Paulo Costeira et al.

The precise estimation of camera poses within large camera networks is a foundational problem in computer vision and robotics, with broad applications spanning autonomous navigation, surveillance, and augmented reality. In this paper, we introduce a novel methodology that extends state-of-the-art Pose Graph Optimization (PGO) techniques. Departing from the conventional PGO paradigm, which primarily relies on camera-camera edges, our approach centers on the introduction of a dynamic element - any rigid object free to move in the scene - whose pose can be reliably inferred from a single image. Specifically, we consider the bipartite graph encompassing cameras, object poses evolving dynamically, and camera-object relative transformations at each time step. This shift not only offers a solution to the challenges encountered in directly estimating relative poses between cameras, particularly in adverse environments, but also leverages the inclusion of numerous object poses to ameliorate and integrate errors, resulting in accurate camera pose estimates. Though our framework retains compatibility with traditional PGO solvers, its efficacy benefits from a custom-tailored optimization scheme. To this end, we introduce an iterative primal-dual algorithm, capable of handling large graphs. Empirical benchmarks, conducted on a new dataset of simulated indoor environments, substantiate the efficacy and efficiency of our approach.

Ankit Shah, Rita Singh, Bhiksha Raj et al.

The escalating rates of gun-related violence and mass shootings represent a significant threat to public safety. Timely and accurate information for law enforcement agencies is crucial in mitigating these incidents. Current commercial gunshot detection systems, while effective, often come with prohibitive costs. This research explores a cost-effective alternative by leveraging acoustic analysis of gunshot recordings, potentially obtainable from ubiquitous devices like cell phones, to not only detect gunshots but also classify the type of firearm used. This paper details a study on deciphering gun type hierarchies using a curated dataset of 3459 recordings. We investigate the fundamental acoustic characteristics of gunshots, including muzzle blasts and shockwaves, which vary based on firearm type, ammunition, and shooting direction. We propose and evaluate machine learning frameworks, including Support Vector Machines (SVMs) as a baseline and a more advanced Convolutional Neural Network (CNN) architecture for joint gunshot detection and gun type classification. Results indicate that our deep learning approach achieves a mean average precision (mAP) of 0.58 on clean labeled data, outperforming the SVM baseline (mAP 0.39). Challenges related to data quality, environmental noise, and the generalization capabilities when using noisy web-sourced data (mAP 0.35) are also discussed. The long-term vision is to develop a highly accurate, real-time system deployable on common recording devices, significantly reducing detection costs and providing critical intelligence to first responders.

Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He et al.

Accurate emotion perception is crucial for various applications, including human-computer interaction, education, and counseling. However, traditional single-modality approaches often fail to capture the complexity of real-world emotional expressions, which are inherently multimodal. Moreover, existing Multimodal Large Language Models (MLLMs) face challenges in integrating audio and recognizing subtle facial micro-expressions. To address this, we introduce the MERR dataset, containing 28,618 coarse-grained and 4,487 fine-grained annotated samples across diverse emotional categories. This dataset enables models to learn from varied scenarios and generalize to real-world applications. Furthermore, we propose Emotion-LLaMA, a model that seamlessly integrates audio, visual, and textual inputs through emotion-specific encoders. By aligning features into a shared space and employing a modified LLaMA model with instruction tuning, Emotion-LLaMA significantly enhances both emotional recognition and reasoning capabilities. Extensive evaluations show Emotion-LLaMA outperforms other MLLMs, achieving top scores in Clue Overlap (7.83) and Label Overlap (6.25) on EMER, an F1 score of 0.9036 on MER2023-SEMI challenge, and the highest UAR (45.59) and WAR (59.37) in zero-shot evaluations on DFEW dataset.

Junwei Liang, Liangliang Cao, Xuehan Xiong et al.

This paper studies how to introduce viewpoint-invariant feature representations that can help action recognition and detection. Although we have witnessed great progress of action recognition in the past decade, it remains challenging yet interesting how to efficiently model the geometric variations in large scale datasets. This paper proposes a novel Spatial-Temporal Alignment Network (STAN) that aims to learn geometric invariant representations for action recognition and action detection. The STAN model is very light-weighted and generic, which could be plugged into existing action recognition models like ResNet3D and the SlowFast with a very low extra computational cost. We test our STAN model extensively on AVA, Kinetics-400, AVA-Kinetics, Charades, and Charades-Ego datasets. The experimental results show that the STAN model can consistently improve the state of the arts in both action detection and action recognition tasks. We will release our data, models and code.

Evangelia Spiliopoulou, Salvador Medina Maza, Eduard Hovy et al.

Social media has become an important tool to share information about crisis events such as natural disasters and mass attacks. Detecting actionable posts that contain useful information requires rapid analysis of huge volume of data in real-time. This poses a complex problem due to the large amount of posts that do not contain any actionable information. Furthermore, the classification of information in real-time systems requires training on out-of-domain data, as we do not have any data from a new emerging crisis. Prior work focuses on models pre-trained on similar event types. However, those models capture unnecessary event-specific biases, like the location of the event, which affect the generalizability and performance of the classifiers on new unseen data from an emerging new event. In our work, we train an adversarial neural model to remove latent event-specific biases and improve the performance on tweet importance classification.

Mandela Patrick, Po-Yao Huang, Yuki Asano et al.

The dominant paradigm for learning video-text representations -- noise contrastive learning -- increases the similarity of the representations of pairs of samples that are known to be related, such as text and video from the same sample, and pushes away the representations of all other pairs. We posit that this last behaviour is too strict, enforcing dissimilar representations even for samples that are semantically-related -- for example, visually similar videos or ones that share the same depicted action. In this paper, we propose a novel method that alleviates this by leveraging a generative model to naturally push these related samples together: each sample's caption must be reconstructed as a weighted combination of other support samples' visual representations. This simple idea ensures that representations are not overly-specialized to individual samples, are reusable across the dataset, and results in representations that explicitly encode semantics shared between samples, unlike noise contrastive learning. Our proposed method outperforms others by a large margin on MSR-VTT, VATEX and ActivityNet, and MSVD for video-to-text and text-to-video retrieval.

Xinru Yang, Haozhi Qi, Mingyang Li et al.

Facial image retrieval plays a significant role in forensic investigations where an untrained witness tries to identify a suspect from a massive pool of images. However, due to the difficulties in describing human facial appearances verbally and directly, people naturally tend to depict by referring to well-known existing images and comparing specific areas of faces with them and it is also challenging to provide complete comparison at each time. Therefore, we propose an end-to-end framework to retrieve facial images with relevance feedback progressively provided by the witness, enabling an exploitation of history information during multiple rounds and an interactive and iterative approach to retrieving the mental image. With no need of any extra annotations, our model can be applied at the cost of a little response effort. We experiment on \texttt{CelebA} and evaluate the performance by ranking percentile and achieve 99\% under the best setting. Since this topic remains little explored to the best of our knowledge, we hope our work can serve as a stepping stone for further research.

Xiaoyu Zhu, Junwei Liang, Alexander Hauptmann

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. We will release our data, models and code.

Po-Yao Huang, Junjie Hu, Xiaojun Chang et al.

Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak different languages biologically share similar visual systems, the potential of achieving better alignment through visual content is promising yet under-explored in unsupervised multimodal MT (MMT). In this paper, we investigate how to utilize visual content for disambiguation and promoting latent space alignment in unsupervised MMT. Our model employs multimodal back-translation and features pseudo visual pivoting in which we learn a shared multilingual visual-semantic embedding space and incorporate visually-pivoted captioning as additional weak supervision. The experimental results on the widely used Multi30K dataset show that the proposed model significantly improves over the state-of-the-art methods and generalizes well when the images are not available at the testing time.

Junwei Liang, Lu Jiang, Alexander Hauptmann

This paper studies the problem of predicting future trajectories of people in unseen cameras of novel scenarios and views. We approach this problem through the real-data-free setting in which the model is trained only on 3D simulation data and applied out-of-the-box to a wide variety of real cameras. We propose a novel approach to learn robust representation through augmenting the simulation training data such that the representation can better generalize to unseen real-world test data. The key idea is to mix the feature of the hardest camera view with the adversarial feature of the original view. We refer to our method as SimAug. We show that SimAug achieves promising results on three real-world benchmarks using zero real training data, and state-of-the-art performance in the Stanford Drone and the VIRAT/ActEV dataset when using in-domain training data.

Lingling Zhang, Xiaojun Chang, Jun Liu et al.

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities.

Zhong Zhou, Isak Czeresnia Etinger, Florian Metze et al.

There is a surging need across the world for protection against gun violence. There are three main areas that we have identified as challenging in research that tries to curb gun violence: temporal location of gunshots, gun type prediction and gun source (shooter) detection. Our task is gun source detection and muzzle head detection, where the muzzle head is the round opening of the firing end of the gun. We would like to locate the muzzle head of the gun in the video visually, and identify who has fired the shot. In our formulation, we turn the problem of muzzle head detection into two sub-problems of human object detection and gun smoke detection. Our assumption is that the muzzle head typically lies between the gun smoke caused by the shot and the shooter. We have interesting results both in bounding the shooter as well as detecting the gun smoke. In our experiments, we are successful in detecting the muzzle head by detecting the gun smoke and the shooter.

Junwei Liang, Lu Jiang, Kevin Murphy et al.

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).

Po-Yao Huang, Xiaojun Chang, Alexander Hauptmann

With the aim of promoting and understanding the multilingual version of image search, we leverage visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations. Specifically, our model attends to different types of textual semantics in two languages and visual objects for fine-grained alignments between sentences and images. We introduce a new objective function which explicitly encourages attention diversity to learn an improved visual-semantic embedding space. We evaluate our model in the German-Image and English-Image matching tasks on the Multi30K dataset, and in the Semantic Textual Similarity task with the English descriptions of visual content. Results show that our model yields a significant performance gain over other methods in all of the three tasks.

Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai et al.

Tremendous variation in the scale of people/head size is a critical problem for crowd counting. To improve the scale invariance of feature representation, recent works extensively employ Convolutional Neural Networks with multi-column structures to handle different scales and resolutions. However, due to the substantial redundant parameters in columns, existing multi-column networks invariably exhibit almost the same scale features in different columns, which severely affects counting accuracy and leads to overfitting. In this paper, we attack this problem by proposing a novel Multi-column Mutual Learning (McML) strategy. It has two main innovations: 1) A statistical network is incorporated into the multi-column framework to estimate the mutual information between columns, which can approximately indicate the scale correlation between features from different columns. By minimizing the mutual information, each column is guided to learn features with different image scales. 2) We devise a mutual learning scheme that can alternately optimize each column while keeping the other columns fixed on each mini-batch training data. With such asynchronous parameter update process, each column is inclined to learn different feature representation from others, which can efficiently reduce the parameter redundancy and improve generalization ability. More remarkably, McML can be applied to all existing multi-column networks and is end-to-end trainable. Extensive experiments on four challenging benchmarks show that McML can significantly improve the original multi-column networks and outperform the other state-of-the-art approaches.

Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai et al.

The aim of crowd counting is to estimate the number of people in images by leveraging the annotation of center positions for pedestrians' heads. Promising progresses have been made with the prevalence of deep Convolutional Neural Networks. Existing methods widely employ the Euclidean distance (i.e., $L_2$ loss) to optimize the model, which, however, has two main drawbacks: (1) the loss has difficulty in learning the spatial awareness (i.e., the position of head) since it struggles to retain the high-frequency variation in the density map, and (2) the loss is highly sensitive to various noises in crowd counting, such as the zero-mean noise, head size changes, and occlusions. Although the Maximum Excess over SubArrays (MESA) loss has been previously proposed to address the above issues by finding the rectangular subregion whose predicted density map has the maximum difference from the ground truth, it cannot be solved by gradient descent, thus can hardly be integrated into the deep learning framework. In this paper, we present a novel architecture called SPatial Awareness Network (SPANet) to incorporate spatial context for crowd counting. The Maximum Excess over Pixels (MEP) loss is proposed to achieve this by finding the pixel-level subregion with high discrepancy to the ground truth. To this end, we devise a weakly supervised learning scheme to generate such region with a multi-branch architecture. The proposed framework can be integrated into existing deep crowd counting methods and is end-to-end trainable. Extensive experiments on four challenging benchmarks show that our method can significantly improve the performance of baselines. More remarkably, our approach outperforms the state-of-the-art methods on all benchmark datasets.

Shizhe Chen, Yuqing Song, Yida Zhao et al.

Contextual reasoning is essential to understand events in long untrimmed videos. In this work, we systematically explore different captioning models with various contexts for the dense-captioning events in video task, which aims to generate captions for different events in the untrimmed video. We propose five types of contexts as well as two categories of event captioning models, and evaluate their contributions for event captioning from both accuracy and diversity aspects. The proposed captioning models are plugged into our pipeline system for the dense video captioning challenge. The overall system achieves the state-of-the-art performance on the dense-captioning events in video task with 9.91 METEOR score on the challenge testing set.

Shizhe Chen, Qin Jin, Alexander Hauptmann

Bilingual lexicon induction, translating words from the source language to the target language, is a long-standing natural language processing task. Recent endeavors prove that it is promising to employ images as pivot to learn the lexicon induction without reliance on parallel corpora. However, these vision-based approaches simply associate words with entire images, which are constrained to translate concrete words and require object-centered images. We humans can understand words better when they are within a sentence with context. Therefore, in this paper, we propose to utilize images and their associated captions to address the limitations of previous approaches. We propose a multi-lingual caption model trained with different mono-lingual multimodal data to map words in different languages into joint spaces. Two types of word representation are induced from the multi-lingual caption model: linguistic features and localized visual features. The linguistic feature is learned from the sentence contexts with visual semantic constraints, which is beneficial to learn translation for words that are less visual-relevant. The localized visual feature is attended to the region in the image that correlates to the word, so that it alleviates the image restriction for salient visual representation. The two types of features are complementary for word translation. Experimental results on multiple language pairs demonstrate the effectiveness of our proposed method, which substantially outperforms previous vision-based approaches without using any parallel sentences or supervision of seed word pairs.

Junwei Liang, Jay D. Aronson, Alexander Hauptmann

Every minute, hundreds of hours of video are uploaded to social media sites and the Internet from around the world. This material creates a visual record of the experiences of a significant percentage of humanity and can help illuminate how we live in the present moment. When properly analyzed, this video can also help analysts to reconstruct events of interest, including war crimes, human rights violations, and terrorist acts. Machine learning and computer vision can play a crucial role in this process. In this technical report, we describe the Video Event Reconstruction and Analysis (VERA) system. This new tool brings together a variety of capabilities we have developed over the past few years (including video synchronization and geolocation to order unstructured videos lacking metadata over time and space, and sound recognition algorithms) to enable the reconstruction and analysis of events captured on video. Among other uses, VERA enables the localization of a shooter from just a few videos that include the sound of gunshots. To demonstrate the efficacy of this suite of tools, we present the results of estimating the shooter's location of the Las Vegas Shooting in 2017 and show that VERA accurately predicts the shooter's location using only the first few gunshots. We then point out future directions that can help improve the system and further reduce unnecessary human labor in the process. All of the components of VERA run through a web interface that enables human-in-the-loop verification to ensure accurate estimations. All relevant source code, including the web interface and machine learning models, is freely available on Github. We hope that researchers and software developers will be inspired to improve and expand this system moving forward to better meet the needs of human rights and public safety.

Soham Ghosh, Anuva Agarwal, Zarana Parekh et al.

The task of retrieving clips within videos based on a given natural language query requires cross-modal reasoning over multiple frames. Prior approaches such as sliding window classifiers are inefficient, while text-clip similarity driven ranking-based approaches such as segment proposal networks are far more complicated. In order to select the most relevant video clip corresponding to the given text description, we propose a novel extractive approach that predicts the start and end frames by leveraging cross-modal interactions between the text and video - this removes the need to retrieve and re-rank multiple proposal segments. Using recurrent networks we encode the two modalities into a joint representation which is then used in different variants of start-end frame predictor networks. Through extensive experimentation and ablative analysis, we demonstrate that our simple and elegant approach significantly outperforms state of the art on two datasets and has comparable performance on a third.

Junwei Liang, Lu Jiang, Juan Carlos Niebles et al.

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.

Siyu Huang, Zhi-Qi Cheng, Xi Li et al.

Inferring universal laws of the environment is an important ability of human intelligence as well as a symbol of general AI. In this paper, we take a step toward this goal such that we introduce a new challenging problem of inferring invariant physical equation from visual scenarios. For instance, teaching a machine to automatically derive the gravitational acceleration formula by watching a free-falling object. To tackle this challenge, we present a novel pipeline comprised of an Observer Engine and a Physicist Engine by respectively imitating the actions of an observer and a physicist in the real world. Generally, the Observer Engine watches the visual scenarios and then extracting the physical properties of objects. The Physicist Engine analyses these data and then summarizing the inherent laws of object dynamics. Specifically, the learned laws are expressed by mathematical equations such that they are more interpretable than the results given by common probabilistic models. Experiments on synthetic videos have shown that our pipeline is able to discover physical equations on various physical worlds with different visual appearances.

Lijun Yu, Dawei Zhang, Xiangqun Chen et al.

We propose a traffic danger recognition model that works with arbitrary traffic surveillance cameras to identify and predict car crashes. There are too many cameras to monitor manually. Therefore, we developed a model to predict and identify car crashes from surveillance cameras based on a 3D reconstruction of the road plane and prediction of trajectories. For normal traffic, it supports real-time proactive safety checks of speeds and distances between vehicles to provide insights about possible high-risk areas. We achieve good prediction and recognition of car crashes without using any labeled training data of crashes. Experiments on the BrnoCompSpeed dataset show that our model can accurately monitor the road, with mean errors of 1.80% for distance measurement, 2.77 km/h for speed measurement, 0.24 m for car position prediction, and 2.53 km/h for speed prediction.

Ankit Shah, Jean Baptiste Lamare, Tuan Nguyen Anh et al.

This paper presents a novel dataset for traffic accidents analysis. Our goal is to resolve the lack of public data for research about automatic spatio-temporal annotations for traffic safety in the roads. Through the analysis of the proposed dataset, we observed a significant degradation of object detection in pedestrian category in our dataset, due to the object sizes and complexity of the scenes. To this end, we propose to integrate contextual information into conventional Faster R-CNN using Context Mining (CM) and Augmented Context Mining (ACM) to complement the accuracy for small pedestrian detection. Our experiments indicate a considerable improvement in object detection accuracy: +8.51% for CM and +6.20% for ACM. Finally, we demonstrate the performance of accident forecasting in our dataset using Faster R-CNN and an Accident LSTM architecture. We achieved an average of 1.684 seconds in terms of Time-To-Accident measure with an Average Precision of 47.25%. Our Webpage for the paper is https://goo.gl/cqK2wE

Ankit Shah, Harini Kesavamoorthy, Poorva Rane et al.

Moments capture a huge part of our lives. Accurate recognition of these moments is challenging due to the diverse and complex interpretation of the moments. Action recognition refers to the act of classifying the desired action/activity present in a given video. In this work, we perform experiments on Moments in Time dataset to recognize accurately activities occurring in 3 second clips. We use state of the art techniques for visual, auditory and spatio temporal localization and develop method to accurately classify the activity in the Moments in Time dataset. Our novel approach of using Visual Based Textual features and fusion techniques performs well providing an overall 89.23 % Top - 5 accuracy on the 20 classes - a significant improvement over the Baseline TRN model.

Siyu Huang, Xi Li, Zhi-Qi Cheng et al.

In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity. This feature is universal both within an image and across different images, indicating the importance of scale invariance of a crowd counting model. Motivated by this, in this paper we propose simple but effective variants of pooling module, i.e., multi-kernel pooling and stacked pooling, to boost the scale invariance of convolutional neural networks (CNNs), benefiting much the crowd density estimation and counting. Specifically, the multi-kernel pooling comprises of pooling kernels with multiple receptive fields to capture the responses at multi-scale local ranges. The stacked pooling is an equivalent form of multi-kernel pooling, while, it reduces considerable computing cost. Our proposed pooling modules do not introduce extra parameters into model and can easily take place of the vanilla pooling layer in implementation. In empirical study on two benchmark crowd counting datasets, the stacked pooling beats the vanilla pooling layer in most cases.

Shizhe Chen, Yuqing Song, Yida Zhao et al.

This notebook paper presents our system in the ActivityNet Dense Captioning in Video task (task 3). Temporal proposal generation and caption generation are both important to the dense captioning task. Therefore, we propose a proposal ranking model to employ a set of effective feature representations for proposal generation, and ensemble a series of caption models enhanced with context information to generate captions robustly on predicted proposals. Our approach achieves the state-of-the-art performance on the dense video captioning task with 8.529 METEOR score on the challenge testing set.

Junwei Liang, Lu Jiang, Liangliang Cao et al.

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.

Siyu Huang, Xi Li, Zhi-Qi Cheng et al.

A key problem in deep multi-attribute learning is to effectively discover the inter-attribute correlation structures. Typically, the conventional deep multi-attribute learning approaches follow the pipeline of manually designing the network architectures based on task-specific expertise prior knowledge and careful network tunings, leading to the inflexibility for various complicated scenarios in practice. Motivated by addressing this problem, we propose an efficient greedy neural architecture search approach (GNAS) to automatically discover the optimal tree-like deep architecture for multi-attribute learning. In a greedy manner, GNAS divides the optimization of global architecture into the optimizations of individual connections step by step. By iteratively updating the local architectures, the global tree-like architecture gets converged where the bottom layers are shared across relevant attributes and the branches in top layers more encode attribute-specific features. Experiments on three benchmark multi-attribute datasets show the effectiveness and compactness of neural architectures derived by GNAS, and also demonstrate the efficiency of GNAS in searching neural architectures.

Ryota Hinami, Junwei Liang, Shin'ichi Satoh et al.

We tackle the problem of learning concept classifiers from videos on the web without using manually labeled data. Although metadata attached to videos (e.g., video titles, descriptions) can be of help collecting training data for the target concept, the collected data is often very noisy. The main challenge is therefore how to select good examples from noisy training data. Previous approaches firstly learn easy examples that are unlikely to be noise and then gradually learn more complex examples. However, hard examples that are much different from easy ones are never learned. In this paper, we propose an approach called multimodal co-training (MMCo) for selecting good examples from noisy training data. MMCo jointly learns classifiers for multiple modalities that complement each other to select good examples. Since MMCo selects examples by consensus of multimodal classifiers, a hard example for one modality can still be used as a training example by exploiting the power of the other modalities. The algorithm is very simple and easily implemented but yields consistent and significant boosts in example selection and classification performance on the FCVID and YouTube8M benchmarks.

Shizhe Chen, Jia Chen, Qin Jin et al.

The topic diversity of open-domain videos leads to various vocabularies and linguistic expressions in describing video contents, and therefore, makes the video captioning task even more challenging. In this paper, we propose an unified caption framework, M&M TGM, which mines multimodal topics in unsupervised fashion from data and guides the caption decoder with these topics. Compared to pre-defined topics, the mined multimodal topics are more semantically and visually coherent and can reflect the topic distribution of videos better. We formulate the topic-aware caption generation as a multi-task learning problem, in which we add a parallel task, topic prediction, in addition to the caption task. For the topic prediction task, we use the mined topics as the teacher to train a student topic prediction model, which learns to predict the latent topics from multimodal contents of videos. The topic prediction provides intermediate supervision to the learning process. As for the caption task, we propose a novel topic-aware decoder to generate more accurate and detailed video descriptions with the guidance from latent topics. The entire learning procedure is end-to-end and it optimizes both tasks simultaneously. The results from extensive experiments conducted on the MSR-VTT and Youtube2Text datasets demonstrate the effectiveness of our proposed model. M&M TGM not only outperforms prior state-of-the-art methods on multiple evaluation metrics and on both benchmark datasets, but also achieves better generalization ability.

Lu Jiang, Junwei Liang, Liangliang Cao et al.

This paper proposes a new task, MemexQA: given a collection of photos or videos from a user, the goal is to automatically answer questions that help users recover their memory about events captured in the collection. Towards solving the task, we 1) present the MemexQA dataset, a large, realistic multimodal dataset consisting of real personal photos and crowd-sourced questions/answers, 2) propose MemexNet, a unified, end-to-end trainable network architecture for image, text and video question answering. Experimental results on the MemexQA dataset demonstrate that MemexNet outperforms strong baselines and yields the state-of-the-art on this novel and challenging task. The promising results on TextQA and VideoQA suggest MemexNet's efficacy and scalability across various QA tasks.

Junwei Liang, Lu Jiang, Deyu Meng et al.

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 are associated with rich but noisy contextual information, such as the title, which provides weak annotations or labels about the video content. To leverage the big noisy web labels, this paper proposes a novel method called WEbly-Labeled Learning (WELL), which is established on the state-of-the-art machine learning algorithm inspired by the learning process of human. WELL introduces a number of novel multi-modal approaches to incorporate meaningful prior knowledge called curriculum from the noisy web videos. To investigate this problem, we empirically study the curriculum constructed from the multi-modal features of the videos collected from YouTube and Flickr. The efficacy and the scalability of WELL have been extensively demonstrated on two public benchmarks, including the largest multimedia dataset and the largest manually-labeled video set. The comprehensive experimental results demonstrate that WELL 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 is robust to the level of noisiness in the video data. Notably, WELL trained on sufficient noisy web labels is able to achieve a comparable accuracy to supervised learning methods trained on the clean manually-labeled data.

Zhenzhong Lan, Dezhong Yao, Ming Lin et al.

Motivated by the success of data-driven convolutional neural networks (CNNs) in object recognition on static images, researchers are working hard towards developing CNN equivalents for learning video features. However, learning video features globally has proven to be quite a challenge due to its high dimensionality, the lack of labelled data and the difficulty in processing large-scale video data. Therefore, we propose to leverage effective techniques from both data-driven and data-independent approaches to improve action recognition system. Our contribution is three-fold. First, we propose a two-stream Stacked Convolutional Independent Subspace Analysis (ConvISA) architecture to show that unsupervised learning methods can significantly boost the performance of traditional local features extracted from data-independent models. Second, we demonstrate that by learning on video volumes detected by Improved Dense Trajectory (IDT), we can seamlessly combine our novel local descriptors with hand-crafted descriptors. Thus we can utilize available feature enhancing techniques developed for hand-crafted descriptors. Finally, similar to multi-class classification framework in CNNs, we propose a training-free re-ranking technique that exploits the relationship among action classes to improve the overall performance. Our experimental results on four benchmark action recognition datasets show significantly improved performance.