Counting people in dense crowds is a demanding task even for humans. This is primarily due to the large variability in appearance of people. Often people are only seen as a bunch of blobs. Occlusions, pose variations and background clutter further compound the difficulty. In this scenario, identifying a person requires larger spatial context and semantics of the scene. But the current state-of-the-art CNN regressors for crowd counting are feedforward and use only limited spatial context to detect people. They look for local crowd patterns to regress the crowd density map, resulting in false predictions. Hence, we propose top-down feedback to correct the initial prediction of the CNN. Our architecture consists of a bottom-up CNN along with a separate top-down CNN to generate feedback. The bottom-up network, which regresses the crowd density map, has two columns of CNN with different receptive fields. Features from various layers of the bottomup CNN are fed to the top-down network. The feedback, thus generated, is applied on the lower layers of the bottom-up network in the form of multiplicative gating. This masking weighs activations of the bottom-up network at spatial as well as feature levels to correct the density prediction. We evaluate the performance of our model on all major crowd datasets and show the effectiveness of top-down feedback.
This study focused in investigating the fuel properties of Castor oil Methyl Ester (CME) and its blend with diesel fuel in running a diesel engine. Engine tests have been carried out with the aim of obtaining comparative measures of torque, power, and specific fuel consumption. Castor oil was extracted by using a mechanical pressing machine and trans-esterification was made by methyl alcohol and potassium hydroxide as a catalyst. So that its viscosity and density were reduced and by increasing its volatility. By following the procedures given in American Society for Testing and Materials (ASTM) book the fuel characteristics were identified whether it fulfil the requirements needed to be used as a fuel in internal combustion engines or not. From the characterization result, it was proved that trans-esterified castor oil was found to be a promising alternative fuel for compression ignition (diesel) engines. But the viscosity of CME was still higher and the energy content was a little bit less as compared to petro diesel. To solve these problems CME was blended with petro diesel in some proportion (B5, B10, B20, B40, B80). The torque, power and brake specific fuel consumption performances of CME and its blends with petro diesel were tested in a four stroke diesel engine. The analyzed results were compared with that of petro diesel and found to be very nearly similar, making CME a suiTable alternative fuel for petro diesel.
The ability to semantically interpret hand-drawn line sketches, although very challenging, can pave way for novel applications in multimedia. We propose SKETCH-PARSE, the first deep-network architecture for fully automatic parsing of freehand object sketches. SKETCHPARSE is configured as a two-level fully convolutional network. The first level contains shared layers common to all object categories. The second level contains a number of expert sub-networks. Each expert specializes in parsing sketches from object categories which contain structurally similar parts. Effectively, the two-level configuration enables our architecture to scale up efficiently as additional categories are added. We introduce a router layer which (i) relays sketch features from shared layers to the correct expert (ii) eliminates the need to manually specify object category during inference. To bypass laborious part-level annotation, we sketchify photos from semantic object-part image datasets and use them for training. Our architecture also incorporates object pose prediction as a novel auxiliary task which boosts overall performance while providing supplementary information regarding the sketch. We demonstrate SKETCHPARSE's abilities (i) on two challenging large-scale sketch datasets (ii) in parsing unseen, semantically related object categories (iii) in improving finegrained sketch-based image retrieval. As a novel application, we also outline how SKETCHPARSE's output can be used to generate caption-style descriptions for hand-drawn sketches.
Deep learning exploits large volumes of labeled data to learn powerful models. When the target dataset is small, it is a common practice to perform transfer learning using pre-trained models to learn new task specific representations. However, pre-trained CNNs for image recognition are provided with limited information about the image during training, which is label alone. Tasks such as scene retrieval suffer from features learned from this weak supervision and require stronger supervision to better understand the contents of the image. In this paper, we exploit the features learned from caption generating models to learn novel task specific image representations. In particular, we consider the state-of-the art captioning system Show and Tell [1] and the dense region description model DenseCap [2]. We demonstrate that, owing to richer supervision provided during the process of training, the features learned by the captioning system perform better than those of CNNs. Further, we train a siamese network with a modified pair-wise loss to fuse the features learned by [1] and [2] and learn image representations suitable for retrieval. Experiments show that the proposed fusion exploits the complementary nature of the individual features and yields stateof-the art retrieval results on benchmark datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.