Bharat Singh

Hidir Yesiltepe, Koutilya PNVR, Gaurav Pathak et al.

Recent progress in video diffusion models has enabled remarkable generative fidelity, yet leveraging these priors for restoration remains limited by the strong coupling between conditional and unconditional branches in standard classifier-free guidance. We introduce a training-free framework that enhances distorted and low-resolution videos by decoupling these signals in time. Our proposed Decoupled Time Guidance (DTG) evaluates the unconditional branch at a cleaner diffusion timestep, providing a lookahead prior that preserves geometry while suppressing replication of warped content. This temporal bias is annealed throughout sampling, allowing the model to transition from structure correction to detail refinement without retraining. Combined with any off-the-shelf restoration module in a plug-and-play manner, our approach improves perceptual coherence and restores plausible structure in AIgenerated and real-world videos alike. To facilitate evaluation, we curate GenWarp480, a benchmark of 4,400 distorted 480p videos synthesized from diverse text-to-video models. GenWarp480 focuses on characteristic generative degradations such as warped faces, body misalignments, and spatial artifacts, providing a purpose-built testbed for assessing robustness to generative errors. Extensive experiments demonstrate that our method achieves significant improvements in structural fidelity and temporal stability without any model training.

Nirat Saini, Navaneeth Bodla, Ashish Shrivastava et al.

We introduce InVi, an approach for inserting or replacing objects within videos (referred to as inpainting) using off-the-shelf, text-to-image latent diffusion models. InVi targets controlled manipulation of objects and blending them seamlessly into a background video unlike existing video editing methods that focus on comprehensive re-styling or entire scene alterations. To achieve this goal, we tackle two key challenges. Firstly, for high quality control and blending, we employ a two-step process involving inpainting and matching. This process begins with inserting the object into a single frame using a ControlNet-based inpainting diffusion model, and then generating subsequent frames conditioned on features from an inpainted frame as an anchor to minimize the domain gap between the background and the object. Secondly, to ensure temporal coherence, we replace the diffusion model's self-attention layers with extended-attention layers. The anchor frame features serve as the keys and values for these layers, enhancing consistency across frames. Our approach removes the need for video-specific fine-tuning, presenting an efficient and adaptable solution. Experimental results demonstrate that InVi achieves realistic object insertion with consistent blending and coherence across frames, outperforming existing methods.

Koutilya Pnvr, Bharat Singh, Pallabi Ghosh et al.

Large-scale pre-training tasks like image classification, captioning, or self-supervised techniques do not incentivize learning the semantic boundaries of objects. However, recent generative foundation models built using text-based latent diffusion techniques may learn semantic boundaries. This is because they have to synthesize intricate details about all objects in an image based on a text description. Therefore, we present a technique for segmenting real and AI-generated images using latent diffusion models (LDMs) trained on internet-scale datasets. First, we show that the latent space of LDMs (z-space) is a better input representation compared to other feature representations like RGB images or CLIP encodings for text-based image segmentation. By training the segmentation models on the latent z-space, which creates a compressed representation across several domains like different forms of art, cartoons, illustrations, and photographs, we are also able to bridge the domain gap between real and AI-generated images. We show that the internal features of LDMs contain rich semantic information and present a technique in the form of LD-ZNet to further boost the performance of text-based segmentation. Overall, we show up to 6% improvement over standard baselines for text-to-image segmentation on natural images. For AI-generated imagery, we show close to 20% improvement compared to state-of-the-art techniques. The project is available at https://koutilya-pnvr.github.io/LD-ZNet/.

Bharat Singh, Mahyar Najibi, Larry S. Davis

We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks. Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances (referred to as chips) at the appropriate scale. For background sampling, these context-regions are generated using proposals extracted from a region proposal network trained with a short learning schedule. Hence, the number of chips generated per image during training adaptively changes based on the scene complexity. SNIPER only processes 30% more pixels compared to the commonly used single scale training at 800x1333 pixels on the COCO dataset. But, it also observes samples from extreme resolutions of the image pyramid, like 1400x2000 pixels. As SNIPER operates on resampled low resolution chips (512x512 pixels), it can have a batch size as large as 20 on a single GPU even with a ResNet-101 backbone. Therefore it can benefit from batch-normalization during training without the need for synchronizing batch-normalization statistics across GPUs. SNIPER brings training of instance level recognition tasks like object detection closer to the protocol for image classification and suggests that the commonly accepted guideline that it is important to train on high resolution images for instance level visual recognition tasks might not be correct. Our implementation based on Faster-RCNN with a ResNet-101 backbone obtains an mAP of 47.6% on the COCO dataset for bounding box detection and can process 5 images per second during inference with a single GPU. Code is available at https://github.com/MahyarNajibi/SNIPER/.

Bharat Singh, Viveka Kulharia, Luyu Yang et al.

Multimodal synthetic data generation is crucial in domains such as autonomous driving, robotics, augmented/virtual reality, and retail. We propose a novel approach, GenMM, for jointly editing RGB videos and LiDAR scans by inserting temporally and geometrically consistent 3D objects. Our method uses a reference image and 3D bounding boxes to seamlessly insert and blend new objects into target videos. We inpaint the 2D Regions of Interest (consistent with 3D boxes) using a diffusion-based video inpainting model. We then compute semantic boundaries of the object and estimate it's surface depth using state-of-the-art semantic segmentation and monocular depth estimation techniques. Subsequently, we employ a geometry-based optimization algorithm to recover the 3D shape of the object's surface, ensuring it fits precisely within the 3D bounding box. Finally, LiDAR rays intersecting with the new object surface are updated to reflect consistent depths with its geometry. Our experiments demonstrate the effectiveness of GenMM in inserting various 3D objects across video and LiDAR modalities.

Bharat Singh, Mahyar Najibi, Abhishek Sharma et al.

We present an efficient foveal framework to perform object detection. A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a fixed size range at different scales. Such a restriction of objects' size during training affords better learning of object-sensitive filters, and therefore, results in better accuracy. However, the use of an image pyramid increases the computational cost. Hence, we propose an efficient spatial sub-sampling scheme which only operates on fixed-size sub-regions likely to contain objects (as object locations are known during training). The resulting approach, referred to as Scale Normalized Image Pyramid with Efficient Resampling or SNIPER, yields up to 3 times speed-up during training. Unfortunately, as object locations are unknown during inference, the entire image pyramid still needs processing. To this end, we adopt a coarse-to-fine approach, and predict the locations and extent of object-like regions which will be processed in successive scales of the image pyramid. Intuitively, it's akin to our active human-vision that first skims over the field-of-view to spot interesting regions for further processing and only recognizes objects at the right resolution. The resulting algorithm is referred to as AutoFocus and results in a 2.5-5 times speed-up during inference when used with SNIP.

Rohun Tripathi, Vasu Singla, Mahyar Najibi et al.

The widely adopted sequential variant of Non Maximum Suppression (or Greedy-NMS) is a crucial module for object-detection pipelines. Unfortunately, for the region proposal stage of two/multi-stage detectors, NMS is turning out to be a latency bottleneck due to its sequential nature. In this article, we carefully profile Greedy-NMS iterations to find that a major chunk of computation is wasted in comparing proposals that are already far-away and have a small chance of suppressing each other. We address this issue by comparing only those proposals that are generated from nearby anchors. The translation-invariant property of the anchor lattice affords generation of a lookup table, which provides an efficient access to nearby proposals, during NMS. This leads to an Accelerated NMS algorithm which leverages Spatially Aware Priors, or ASAP-NMS, and improves the latency of the NMS step from 13.6ms to 1.2 ms on a CPU without sacrificing the accuracy of a state-of-the-art two-stage detector on COCO and VOC datasets. Importantly, ASAP-NMS is agnostic to image resolution and can be used as a simple drop-in module during inference. Using ASAP-NMS at run-time only, we obtain an mAP of 44.2\%@25Hz on the COCO dataset with a V100 GPU.

Rohun Tripathi, Bharat Singh

We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces the loss on a mini-batch. If this reduces the loss, the weight is updated, otherwise the existing weight is retained. Surprisingly, we find that repeating this process a few times for each weight is sufficient to train a deep neural network. The number of weight updates for RSO is an order of magnitude lesser when compared to backpropagation with SGD. RSO can make aggressive weight updates in each step as there is no concept of learning rate. The weight update step for individual layers is also not coupled with the magnitude of the loss. RSO is evaluated on classification tasks on MNIST and CIFAR-10 datasets with deep neural networks of 6 to 10 layers where it achieves an accuracy of 99.1% and 81.8% respectively. We also find that after updating the weights just 5 times, the algorithm obtains a classification accuracy of 98% on MNIST.

Zhe Wu, Zuxuan Wu, Bharat Singh et al.

Deep neural networks have been shown to suffer from poor generalization when small perturbations are added (like Gaussian noise), yet little work has been done to evaluate their robustness to more natural image transformations like photo filters. This paper presents a study on how popular pretrained models are affected by commonly used Instagram filters. To this end, we introduce ImageNet-Instagram, a filtered version of ImageNet, where 20 popular Instagram filters are applied to each image in ImageNet. Our analysis suggests that simple structure preserving filters which only alter the global appearance of an image can lead to large differences in the convolutional feature space. To improve generalization, we introduce a lightweight de-stylization module that predicts parameters used for scaling and shifting feature maps to "undo" the changes incurred by filters, inverting the process of style transfer tasks. We further demonstrate the module can be readily plugged into modern CNN architectures together with skip connections. We conduct extensive studies on ImageNet-Instagram, and show quantitatively and qualitatively, that the proposed module, among other things, can effectively improve generalization by simply learning normalization parameters without retraining the entire network, thus recovering the alterations in the feature space caused by the filters.

Chongyang Bai, Maksim Bolonkin, Judee Burgoon et al.

Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video. In this paper, we propose a new ADD framework which captures long term deception in a group setting. We study deception in the well-known Resistance game (like Mafia and Werewolf) which consists of 5-8 players of whom 2-3 are spies. Spies are deceptive throughout the game (typically 30-65 minutes) to keep their identity hidden. We develop an ensemble predictive model to identify spies in Resistance videos. We show that features from low-level and high-level video analysis are insufficient, but when combined with a new class of features that we call LiarRank, produce the best results. We achieve AUCs of over 0.70 in a fully automated setting. Our demo can be found at http://home.cs.dartmouth.edu/~mbolonkin/scan/demo/

Hengduo Li, Bharat Singh, Mahyar Najibi et al.

We provide a detailed analysis of convolutional neural networks which are pre-trained on the task of object detection. To this end, we train detectors on large datasets like OpenImagesV4, ImageNet Localization and COCO. We analyze how well their features generalize to tasks like image classification, semantic segmentation and object detection on small datasets like PASCAL-VOC, Caltech-256, SUN-397, Flowers-102 etc. Some important conclusions from our analysis are --- 1) Pre-training on large detection datasets is crucial for fine-tuning on small detection datasets, especially when precise localization is needed. For example, we obtain 81.1% mAP on the PASCAL-VOC dataset at 0.7 IoU after pre-training on OpenImagesV4, which is 7.6% better than the recently proposed DeformableConvNetsV2 which uses ImageNet pre-training. 2) Detection pre-training also benefits other localization tasks like semantic segmentation but adversely affects image classification. 3) Features for images (like avg. pooled Conv5) which are similar in the object detection feature space are likely to be similar in the image classification feature space but the converse is not true. 4) Visualization of features reveals that detection neurons have activations over an entire object, while activations for classification networks typically focus on parts. Therefore, detection networks are poor at classification when multiple instances are present in an image or when an instance only covers a small fraction of an image.

Xiyang Dai, Bharat Singh, Joe Yue-Hei Ng et al.

We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks. By stacking spatial and temporal convolutions repeatedly, TAN forms a deep hierarchical representation for capturing spatio-temporal information in videos. Since we do not apply 3D convolutions in each layer but only apply temporal aggregation blocks once after each spatial downsampling layer in the network, we significantly reduce the model complexity. The use of dilated convolutions at different resolutions of the network helps in aggregating multi-scale spatio-temporal information efficiently. Experiments show that our model is well suited for dense multi-label action recognition, which is a challenging sub-topic of action recognition that requires predicting multiple action labels in each frame. We outperform state-of-the-art methods by 5% and 3% on the Charades and Multi-THUMOS dataset respectively.

Mahyar Najibi, Bharat Singh, Larry S. Davis

We propose a novel approach for generating region proposals for performing face-detection. Instead of classifying anchor boxes using features from a pixel in the convolutional feature map, we adopt a pooling-based approach for generating region proposals. However, pooling hundreds of thousands of anchors which are evaluated for generating proposals becomes a computational bottleneck during inference. To this end, an efficient anchor placement strategy for reducing the number of anchor-boxes is proposed. We then show that proposals generated by our network (Floating Anchor Region Proposal Network, FA-RPN) are better than RPN for generating region proposals for face detection. We discuss several beneficial features of FA-RPN proposals like iterative refinement, placement of fractional anchors and changing anchors which can be enabled without making any changes to the trained model. Our face detector based on FA-RPN obtains 89.4% mAP with a ResNet-50 backbone on the WIDER dataset.

Mahyar Najibi, Bharat Singh, Larry S. Davis

This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales. This is achieved by predicting category agnostic segmentation maps for small objects at coarser scales, called FocusPixels. FocusPixels can be predicted with high recall, and in many cases, they only cover a small fraction of the entire image. To make efficient use of FocusPixels, an algorithm is proposed which generates compact rectangular FocusChips which enclose FocusPixels. The detector is only applied inside FocusChips, which reduces computation while processing finer scales. Different types of error can arise when detections from FocusChips of multiple scales are combined, hence techniques to correct them are proposed. AutoFocus obtains an mAP of 47.9% (68.3% at 50% overlap) on the COCO test-dev set while processing 6.4 images per second on a Titan X (Pascal) GPU. This is 2.5X faster than our multi-scale baseline detector and matches its mAP. The number of pixels processed in the pyramid can be reduced by 5X with a 1% drop in mAP. AutoFocus obtains more than 10% mAP gain compared to RetinaNet but runs at the same speed with the same ResNet-101 backbone.

Zhe Wu, Navaneeth Bodla, Bharat Singh et al.

We study the robustness of object detection under the presence of missing annotations. In this setting, the unlabeled object instances will be treated as background, which will generate an incorrect training signal for the detector. Interestingly, we observe that after dropping 30% of the annotations (and labeling them as background), the performance of CNN-based object detectors like Faster-RCNN only drops by 5% on the PASCAL VOC dataset. We provide a detailed explanation for this result. To further bridge the performance gap, we propose a simple yet effective solution, called Soft Sampling. Soft Sampling re-weights the gradients of RoIs as a function of overlap with positive instances. This ensures that the uncertain background regions are given a smaller weight compared to the hardnegatives. Extensive experiments on curated PASCAL VOC datasets demonstrate the effectiveness of the proposed Soft Sampling method at different annotation drop rates. Finally, we show that on OpenImagesV3, which is a real-world dataset with missing annotations, Soft Sampling outperforms standard detection baselines by over 3%.

Zhe Wu, Bharat Singh, Larry S. Davis et al.

We present a system for covert automated deception detection in real-life courtroom trial videos. We study the importance of different modalities like vision, audio and text for this task. On the vision side, our system uses classifiers trained on low level video features which predict human micro-expressions. We show that predictions of high-level micro-expressions can be used as features for deception prediction. Surprisingly, IDT (Improved Dense Trajectory) features which have been widely used for action recognition, are also very good at predicting deception in videos. We fuse the score of classifiers trained on IDT features and high-level micro-expressions to improve performance. MFCC (Mel-frequency Cepstral Coefficients) features from the audio domain also provide a significant boost in performance, while information from transcripts is not very beneficial for our system. Using various classifiers, our automated system obtains an AUC of 0.877 (10-fold cross-validation) when evaluated on subjects which were not part of the training set. Even though state-of-the-art methods use human annotations of micro-expressions for deception detection, our fully automated approach outperforms them by 5%. When combined with human annotations of micro-expressions, our AUC improves to 0.922. We also present results of a user-study to analyze how well do average humans perform on this task, what modalities they use for deception detection and how they perform if only one modality is accessible. Our project page can be found at \url{https://doubaibai.github.io/DARE/}.

Bharat Singh, Hengduo Li, Abhishek Sharma et al.

We present R-FCN-3000, a large-scale real-time object detector in which objectness detection and classification are decoupled. To obtain the detection score for an RoI, we multiply the objectness score with the fine-grained classification score. Our approach is a modification of the R-FCN architecture in which position-sensitive filters are shared across different object classes for performing localization. For fine-grained classification, these position-sensitive filters are not needed. R-FCN-3000 obtains an mAP of 34.9% on the ImageNet detection dataset and outperforms YOLO-9000 by 18% while processing 30 images per second. We also show that the objectness learned by R-FCN-3000 generalizes to novel classes and the performance increases with the number of training object classes - supporting the hypothesis that it is possible to learn a universal objectness detector. Code will be made available.

Bharat Singh, Larry S. Davis

An analysis of different techniques for recognizing and detecting objects under extreme scale variation is presented. Scale specific and scale invariant design of detectors are compared by training them with different configurations of input data. By evaluating the performance of different network architectures for classifying small objects on ImageNet, we show that CNNs are not robust to changes in scale. Based on this analysis, we propose to train and test detectors on the same scales of an image-pyramid. Since small and large objects are difficult to recognize at smaller and larger scales respectively, we present a novel training scheme called Scale Normalization for Image Pyramids (SNIP) which selectively back-propagates the gradients of object instances of different sizes as a function of the image scale. On the COCO dataset, our single model performance is 45.7% and an ensemble of 3 networks obtains an mAP of 48.3%. We use off-the-shelf ImageNet-1000 pre-trained models and only train with bounding box supervision. Our submission won the Best Student Entry in the COCO 2017 challenge. Code will be made available at \url{http://bit.ly/2yXVg4c}.

Xiyang Dai, Bharat Singh, Guyue Zhang et al.

We present a Temporal Context Network (TCN) for precise temporal localization of human activities. Similar to the Faster-RCNN architecture, proposals are placed at equal intervals in a video which span multiple temporal scales. We propose a novel representation for ranking these proposals. Since pooling features only inside a segment is not sufficient to predict activity boundaries, we construct a representation which explicitly captures context around a proposal for ranking it. For each temporal segment inside a proposal, features are uniformly sampled at a pair of scales and are input to a temporal convolutional neural network for classification. After ranking proposals, non-maximum suppression is applied and classification is performed to obtain final detections. TCN outperforms state-of-the-art methods on the ActivityNet dataset and the THUMOS14 dataset.

Navaneeth Bodla, Bharat Singh, Rama Chellappa et al.

Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with M are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss. To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process. Soft-NMS obtains consistent improvements for the coco-style mAP metric on standard datasets like PASCAL VOC 2007 (1.7% for both R-FCN and Faster-RCNN) and MS-COCO (1.3% for R-FCN and 1.1% for Faster-RCNN) by just changing the NMS algorithm without any additional hyper-parameters. Using Deformable-RFCN, Soft-NMS improves state-of-the-art in object detection from 39.8% to 40.9% with a single model. Further, the computational complexity of Soft-NMS is the same as traditional NMS and hence it can be efficiently implemented. Since Soft-NMS does not require any extra training and is simple to implement, it can be easily integrated into any object detection pipeline. Code for Soft-NMS is publicly available on GitHub (http://bit.ly/2nJLNMu).

Carlos Castillo, Soham De, Xintong Han et al.

Style transfer is an important task in which the style of a source image is mapped onto that of a target image. The method is useful for synthesizing derivative works of a particular artist or specific painting. This work considers targeted style transfer, in which the style of a template image is used to alter only part of a target image. For example, an artist may wish to alter the style of only one particular object in a target image without altering the object's general morphology or surroundings. This is useful, for example, in augmented reality applications (such as the recently released Pokemon GO), where one wants to alter the appearance of a single real-world object in an image frame to make it appear as a cartoon. Most notably, the rendering of real-world objects into cartoon characters has been used in a number of films and television show, such as the upcoming series Son of Zorn. We present a method for targeted style transfer that simultaneously segments and stylizes single objects selected by the user. The method uses a Markov random field model to smooth and anti-alias outlier pixels near object boundaries, so that stylized objects naturally blend into their surroundings.

Seyed A. Esmaeili, Bharat Singh, Larry S. Davis

Fast-AT is an automatic thumbnail generation system based on deep neural networks. It is a fully-convolutional deep neural network, which learns specific filters for thumbnails of different sizes and aspect ratios. During inference, the appropriate filter is selected depending on the dimensions of the target thumbnail. Unlike most previous work, Fast-AT does not utilize saliency but addresses the problem directly. In addition, it eliminates the need to conduct region search on the saliency map. The model generalizes to thumbnails of different sizes including those with extreme aspect ratios and can generate thumbnails in real time. A data set of more than 70,000 thumbnail annotations was collected to train Fast-AT. We show competitive results in comparison to existing techniques.

Gavin Taylor, Ryan Burmeister, Zheng Xu et al.

With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient methods that don't scale well to large numbers of cores in a cluster setting. Furthermore, the convergence of all gradient methods, including batch methods, suffers from common problems like saturation effects, poor conditioning, and saddle points. This paper explores an unconventional training method that uses alternating direction methods and Bregman iteration to train networks without gradient descent steps. The proposed method reduces the network training problem to a sequence of minimization sub-steps that can each be solved globally in closed form. The proposed method is advantageous because it avoids many of the caveats that make gradient methods slow on highly non-convex problems. The method exhibits strong scaling in the distributed setting, yielding linear speedups even when split over thousands of cores.

Xintong Han, Bharat Singh, Vlad I. Morariu et al.

VRFP is a real-time video retrieval framework based on short text input queries, which obtains weakly labeled training images from the web after the query is known. The retrieved web images representing the query and each database video are treated as unordered collections of images, and each collection is represented using a single Fisher Vector built on CNN features. Our experiments show that a Fisher Vector is robust to noise present in web images and compares favorably in terms of accuracy to other standard representations. While a Fisher Vector can be constructed efficiently for a new query, matching against the test set is slow due to its high dimensionality. To perform matching in real-time, we present a lossless algorithm that accelerates the inner product computation between high dimensional Fisher Vectors. We prove that the expected number of multiplications required decreases quadratically with the sparsity of Fisher Vectors. We are not only able to construct and apply query models in real-time, but with the help of a simple re-ranking scheme, we also outperform state-of-the-art automatic retrieval methods by a significant margin on TRECVID MED13 (3.5%), MED14 (1.3%) and CCV datasets (5.2%). We also provide a direct comparison on standard datasets between two different paradigms for automatic video retrieval - zero-shot learning and on-the-fly retrieval.

Bharat Singh, Soham De, Yangmuzi Zhang et al.

The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to vanishing gradients, in which the gradients used by back-propagation are extremely large for weights connecting deep layers (layers near the output layer), and extremely small for shallow layers (near the input layer); this results in slow learning in the shallow layers. Additionally, it has also been shown that in highly non-convex problems, such as deep neural networks, there is a proliferation of high-error low curvature saddle points, which slows down learning dramatically. In this paper, we attempt to overcome the two above problems by proposing an optimization method for training deep neural networks which uses learning rates which are both specific to each layer in the network and adaptive to the curvature of the function, increasing the learning rate at low curvature points. This enables us to speed up learning in the shallow layers of the network and quickly escape high-error low curvature saddle points. We test our method on standard image classification datasets such as MNIST, CIFAR10 and ImageNet, and demonstrate that our method increases accuracy as well as reduces the required training time over standard algorithms.

Bharat Singh, Xintong Han, Zhe Wu et al.

Complex event retrieval is a challenging research problem, especially when no training videos are available. An alternative to collecting training videos is to train a large semantic concept bank a priori. Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos. However, defining an exhaustive concept lexicon and pre-training it requires vast computational resources. Therefore, recent approaches automate concept discovery and training by leveraging large amounts of weakly annotated web data. Compact visually salient concepts are automatically obtained by the use of concept pairs or, more generally, n-grams. However, not all visually salient n-grams are necessarily useful for an event query--some combinations of concepts may be visually compact but irrelevant--and this drastically affects performance. We propose an event retrieval algorithm that constructs pairs of automatically discovered concepts and then prunes those concepts that are unlikely to be helpful for retrieval. Pruning depends both on the query and on the specific video instance being evaluated. Our approach also addresses calibration and domain adaptation issues that arise when applying concept detectors to unseen videos. We demonstrate large improvements over other vision based systems on the TRECVID MED 13 dataset.