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/.

Traditional scene graph generation methods are trained using cross-entropy losses that treat objects and relationships as independent entities. Such a formulation, however, ignores the structure in the output space, in an inherently structured prediction problem. In this work, we introduce a novel energy-based learning framework for generating scene graphs. The proposed formulation allows for efficiently incorporating the structure of scene graphs in the output space. This additional constraint in the learning framework acts as an inductive bias and allows models to learn efficiently from a small number of labels. We use the proposed energy-based framework†to train existing stateof-the-art models and obtain a significant performance improvement, of up to 21% and 27%, on the Visual Genome [9] and GQA [5] benchmark datasets, respectively. Furthermore, we showcase the learning efficiency of the proposed framework by demonstrating superior performance in the zero- and few-shot settings where data is scarce.

Collaborative problem solving (CPS) is seen as a key skill in K-12 education---in computer science as well as other subjects. Efforts to introduce children to computing rely on pair programming as a way of having young learners engage in CPS. Characteristics of quality collaboration are joint exploring or understanding, joint representation, and joint execution. We present a data driven approach to assessing and elucidating collaboration through modeling of multimodal student behavior and performance data.

We introduce the Tower Game Dataset for computational modeling of social interaction predicates. Existing research in affective computing has focused primarily on recognizing the emotional and mental state of a human based on external behaviors. Recent research in the social science community argues that engaged and sustained social interactions require the participants to jointly coordinate their verbal and non-verbal behaviors. With this as our guiding principle, we collected the Tower Game Dataset consisting of multimodal recordings of two players participating in a tower building game, in the process communicating and collaborating with each other. The format of the game was specifically chosen as it elicits spontaneous communication from the participants through social interaction predicates such as joint attention and entrainment. The dataset will be made public and we believe that it will foster new research in the area of computational social interaction modeling.

We present a new technique for detecting audio concepts in web content as well outline the technique's applications to video sequence parsing. Our focus is primarily on affective concepts and in order to study them we have collected a new dataset, consisting of videos where a speaker is persuading a crowd, called “Rallying a Crowd”. We develop new classifiers for graded levels of arousal in speech as well as crowd noise and music and demonstrate their effectiveness on web content. These techniques achieve high detection accuracy (58.2%) for affective concepts on this new dataset and outperform (36.8%) state-of-the-art techniques (33.1%) for semantic concepts on a previously collected dataset. We also develop a new audio sequence segmentation technique which enables us to rapidly classify subsections of test sequence audio into the aforementioned audio classes. We are thus able to robustly address the detection of affective concepts in highly variable web content as well as the computational challenge of quick classification so as to enable web scale processing.

We introduce the task of automatically classifying politically persuasive web videos and propose a highly effective multi-modal approach for this task. We extract audio, visual, and textual features that attempt to capture affect and semantics in the audio-visual content and sentiment in the viewers' comments. We demonstrate that each of the feature modalities can be used to classify politically persuasive content, and that fusing them leads to the best performance. We also perform experiments to examine human accuracy and inter-coder reliability for this task and show that our best automatic classifier slightly outperforms average human performance. Finally we show that politically persuasive videos generate more strongly negative viewer comments than non-persuasive videos and analyze how affective content can be used to predict viewer reactions.

We propose a novel staged hybrid model for emotion detection in speech. Hybrid models exploit the strength of discriminative classifiers along with the representational power of generative models. Discriminative classifiers have been shown to achieve higher performances than the corresponding generative likelihood-based classifiers. On the other hand, generative models learn a rich informative representations. Our proposed hybrid model consists of a generative model, which is used for unsupervised representation learning of short term temporal phenomena and a discriminative model, which is used for event detection and classification of long range temporal dynamics. We evaluate our approach on multiple audio-visual datasets (AVEC, VAM, and SPD) and demonstrate its superiority compared to the state-of-the-art.

We propose a unified framework for image retrieval capable of handling complex and descriptive queries of multiple modalities in a scalable manner. A novel aspect of our approach is that it supports query specification in terms of objects, attributes and spatial relationships, thereby allowing for substantially more complex and descriptive queries. We allow these complex queries to be specified in three different modalities - images, sketches and structured textual descriptions. Furthermore, we propose a unique multi-modal hashing algorithm capable of mapping queries of different modalities to the same binary representation, enabling efficient and scalable image retrieval based on multi-modal queries. Extensive experimental evaluation shows that our approach outperforms the state-of-the-art image retrieval and hashing techniques on the MSRC and SUN09 datasets by about 100%, while the performance on a dataset of 1M images, from Flickr, demonstrates its scalability.

We propose a novel hybrid model that exploits the strength of discriminative classifiers along with the representational power of generative models. Our focus is on detecting multimodal events in time varying sequences. Discriminative classifiers have been shown to achieve higher performances than the corresponding generative likelihood-based classifiers. On the other hand, generative models learn a rich informative space which allows for data generation and joint feature representation that discriminative models lack. We employ a deep temporal generative model for unsupervised learning of a shared representation across multiple modalities with time varying data. The temporal generative model takes into account short term temporal phenomena and allows for filling in missing data by generating data within or across modalities. The hybrid model involves augmenting the temporal generative model with a temporal discriminative model for event detection, and classification, which enables modeling long range temporal dynamics. We evaluate our approach on audio-visual datasets (AVEC, AVLetters, and CUAVE) and demonstrate its superiority compared to the state-of-the-art.

We present a novel approach for multi-modal affect analysis in human interactions that is capable of integrating data from multiple modalities while also taking into account temporal dynamics. Our fusion approach, Joint Hidden Conditional Random Fields (JHRCFs), combines the advantages of purely feature level (early fusion) fusion approaches with late fusion (CRFs on individual modalities) to simultaneously learn the correlations between features from multiple modalities as well as their temporal dynamics. Our approach addresses major shortcomings of other fusion approaches such as the domination of other modalities by a single modality with early fusion and the loss of cross-modal information with late fusion. Extensive results on the AVEC 2011 dataset show that we outperform the state-of-the-art on the Audio Sub-Challenge, while achieving competitive performance on the Video Sub-Challenge and the Audiovisual Sub-Challenge.

We study the use of domain adaptation and transfer learning techniques as part of a framework for adaptive object detection. Unlike recent applications of domain adaptation work in computer vision, which generally focus on image classification, we explore the problem of extreme class imbalance present when performing domain adaptation for object detection. The main difficulty caused by this imbalance is that test images contain millions or billions of negative image subwindows but just a few image subwindows containing positive instances, which makes it difficult to adapt to changes in the positive classes present new domains by simple techniques such as random sampling. We propose an initial approach to addressing this problem and apply our technique to vehicle detection in a challenging urban surveillance dataset, demonstrating the performance of our approach with various amounts of supervision, including the fully unsupervised case.

We address the problem of learning robust and efficient multi-view object detectors for surveillance video indexing and retrieval. Our philosophy is that effective solutions for this problem can be obtained by learning detectors from huge amounts of training data. Along this research direction, we propose a novel approach that consists of strategically partitioning the training set and learning a large array of complementary, compact, deep cascade detectors. At test time, given a video sequence captured by a fixed camera, a small number of detectors is automatically selected per image location. We demonstrate our approach on the problem of vehicle detection in challenging surveillance scenarios, using a large training dataset composed of around one million images. Our system runs at an impressive average rate of 125 frames per second on a conventional laptop computer.

We present a novel approach for visual detection and attribute-based search of vehicles in crowded surveillance scenes. Large-scale processing is addressed along two dimensions: 1) large-scale indexing, where hundreds of billions of events need to be archived per month to enable effective search and 2) learning vehicle detectors with large-scale feature selection, using a feature pool containing millions of feature descriptors. Our method for vehicle detection also explicitly models occlusions and multiple vehicle types (e.g., buses, trucks, SUVs, cars), while requiring very few manual labeling. It runs quite efficiently at an average of 66 Hz on a conventional laptop computer. Once a vehicle is detected and tracked over the video, fine-grained attributes are extracted and ingested into a database to allow future search queries such as “Show me all blue trucks larger than 7 ft. length traveling at high speed northbound last Saturday, from 2 pm to 5 pm”. We perform a comprehensive quantitative analysis to validate our approach, showing its usefulness in realistic urban surveillance settings.

We propose a novel approach for ranking and retrieval of images based on multi-attribute queries. Existing image retrieval methods train separate classifiers for each word and heuristically combine their outputs for retrieving multiword queries. Moreover, these approaches also ignore the interdependencies among the query terms. In contrast, we propose a principled approach for multi-attribute retrieval which explicitly models the correlations that are present between the attributes. Given a multi-attribute query, we also utilize other attributes in the vocabulary which are not present in the query, for ranking/retrieval. Furthermore, we integrate ranking and retrieval within the same formulation, by posing them as structured prediction problems. Extensive experimental evaluation on the Labeled Faces in the Wild(LFW), FaceTracer and PASCAL VOC datasets show that our approach significantly outperforms several state-of-the-art ranking and retrieval methods.

We present a novel application for searching for vehicles in surveillance videos based on semantic attributes. At the interface, the user specifies a set of vehicle characteristics (such as color, direction of travel, speed, length, height, etc.) and the system automatically retrieves video events that match the provided description. A key differentiating aspect of our system is the ability to handle challenging urban conditions such as high volumes of activity and environmental factors. This is achieved through a novel multi-view vehicle detection approach which relies on what we call motionlet classifiers, i.e. classifiers that are learned with vehicle samples clustered in the motion configuration space. We employ massively parallel feature selection to learn compact and accurate motionlet detectors. Moreover, in order to deal with different vehicle types (buses, trucks, SUVs, cars), we learn the motionlet detectors in a shape-free appearance space, where all training samples are resized to the same aspect ratio, and then during test time the aspect ratio of the sliding window is changed to allow the detection of different vehicle types. Once a vehicle is detected and tracked over the video, fine-grained attributes are extracted and ingested into a database to allow future search queries such as "Show me all blue trucks larger than 7ft length traveling at high speed northbound last Saturday, from 2pm to 5pm".

We present a novel approach for vehicle detection in urban surveillance videos, capable of handling unstructured and crowded environments with large occlusions, different vehicle shapes, and environmental conditions such as lighting changes, rain, shadows, and reflections. This is achieved with virtually no manual labeling efforts. The system runs quite efficiently at an average of 66Hz on a conventional laptop computer. Our proposed approach relies on three key contributions: (1) a co-training scheme where data is automatically captured based on motion and shape cues and used to train a detector based on appearance information; (2) an occlusion handling technique based on synthetically generated training samples obtained through Poisson image reconstruction from image gradients; (3) massively parallel feature selection over multiple feature planes which allows the final detector to be more accurate and more efficient. We perform a comprehensive quantitative analysis to validate our approach, showing its usefulness in realistic urban surveillance settings.

We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class active learning approaches have focused on utilizing classification uncertainty of regions to select the most ambiguous region for labeling. These approaches, however, ignore the contextual interactions between different regions of the image and the fact that knowing the label for one region provides information about the labels of other regions. For example, the knowledge of a region being sea is informative about regions satisfying the “on” relationship with respect to it, since they are highly likely to be boats. We explicitly model the contextual interactions between regions and select the question which leads to the maximum reduction in the combined entropy of all the regions in the image (image entropy). We also introduce a new methodology of posing labeling questions, mimicking the way humans actively learn about their environment. In these questions, we utilize the regions linked to a concept with high confidence as anchors, to pose questions about the uncertain regions. For example, if we can recognize water in an image then we can use the region associated with water as an anchor to pose questions such as “what is above water?”. Our active learning framework also introduces questions which help in actively learning contextual concepts. For example, our approach asks the annotator: “What is the relationship between boat and water?” and utilizes the answer to reduce the image entropies throughout the training dataset and obtain more relevant training examples for appearance models.

A good training dataset, representative of the test images expected in a given application, is critical for ensuring good performance of a visual categorization system. Obtaining task specific datasets of visual categories is, however, far more tedious than obtaining a generic dataset of the same classes. We propose an Incremental Multiple Kernel Learning (IMKL) approach to object recognition that initializes on a generic training database and then tunes itself to the classification task at hand. Our system simultaneously updates the training dataset as well as the weights used to combine multiple information sources. We demonstrate our system on a vehicle classification problem in a video stream overlooking a traffic intersection. Our system updates itself with images of vehicles in poses more commonly observed in the scene, as well as with image patches of the background, leading to an increase in performance. A considerable change in the kernel combination weights is observed as the system gathers scene specific training data over time. The system is also seen to adapt itself to the illumination change in the scene as day transitions to night.

We investigate the problem of combining multiple feature channels for the purpose of efficient image classification. Discriminative kernel based methods, such as SVMs, have been shown to be quite effective for image classification. To use these methods with several feature channels, one needs to combine base kernels computed from them. Multiple kernel learning is an effective method for combining the base kernels. However, the cost of computing the kernel similarities of a test image with each of the support vectors for all feature channels is extremely high. We propose an alternate method, where training data instances are selected, using AdaBoost, for each of the base kernels. A composite decision function, which can be evaluated by computing kernel similarities with respect to only these chosen instances, is learnt. This method significantly reduces the number of kernel computations required during testing. Experimental results on the benchmark UCI datasets, as well as on a challenging painting dataset, are included to demonstrate the effectiveness of our method.

We focus on the problem of automatically extracting the 3D configuration of human poses from 2D image features tracked over a finite interval of time . This problem is highly non-linear in nature and confounds standard regression techniques. Our approach effectively marries a non-rigid factorization algorithm with prior learned statistical models from archival motion capture database. We show that a stand alone non-rigid factorization algorithm is highly unsuitable for this problem. However, when coupled with the learned statistical model in the form of a constrained non- linear programming method, it yields a substantially better solution.