Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of pre-trained vision-language models such as CLIP to identify novel categories. They typically adopt a cascaded pipeline to first detect objects and then classify relationships based on the detected objects, which may lead to error propagation and thus suboptimal performance. In this paper, we propose Mutual EnhancemenT of Objects and Relationships (METOR), a query-based unified framework to jointly model and mutually enhance object detection and relationship classification in open-vocabulary scenarios. Under this framework, we first design a CLIP-based contextual refinement encoding module that extracts visual contexts of objects and relationships to refine the encoding of text features and object queries, thus improving the generalization of encoding to novel categories. Then we propose an iterative enhancement module to alternatively enhance the representations of objects and relationships by fully exploiting their interdependence to improve recognition performance. Extensive experiments on two public datasets, VidVRD and VidOR, demonstrate that our framework achieves state-of-the-art performance.
Visual Relationship Detection (VRD) has seen significant advancements with Transformer-based architectures recently. However, we identify two key limitations in a conventional label assignment for training Transformer-based VRD models, which is a process of mapping a ground-truth (GT) to a prediction. Under the conventional assignment, an unspecialized query is trained since a query is expected to detect every relation, which makes it difficult for a query to specialize in specific relations. Furthermore, a query is also insufficiently trained since a GT is assigned only to a single prediction, therefore near-correct or even correct predictions are suppressed by being assigned no relation as a GT. To address these issues, we propose Groupwise Query Specialization and Quality-Aware Multi-Assignment (SpeaQ). Groupwise Query Specialization trains a specialized query by dividing queries and relations into disjoint groups and directing a query in a specific query group solely toward relations in the corresponding relation group. Quality-Aware Multi-Assignment further facilitates the training by assigning a GT to multiple predictions that are significantly close to a GT in terms of a subject, an object, and the relation in between. Experimental results and analyses show that SpeaQ effectively trains specialized queries, which better utilize the capacity of a model, resulting in consistent performance gains with zero additional inference cost across multiple VRD models and benchmarks. Code is available at https://github.com/mlvlab/SpeaQ.
Machine comprehension of visual information from images and videos by neural networks faces two primary challenges. Firstly, there exists a computational and inference gap in connecting vision and language, making it difficult to accurately determine which object a given agent acts on and represent it through language. Secondly, classifiers trained by a single, monolithic neural network often lack stability and generalization. To overcome these challenges, we introduce MoE-VRD, a novel approach to visual relationship detection utilizing a mixture of experts. MoE-VRD identifies language triplets in the form of < subject, predicate, object> tuples to extract relationships from visual processing. Leveraging recent advancements in visual relationship detection, MoE-VRD addresses the requirement for action recognition in establishing relationships between subjects (acting) and objects (being acted upon). In contrast to single monolithic networks, MoE-VRD employs multiple small models as experts, whose outputs are aggregated. Each expert in MoE-VRD specializes in visual relationship learning and object tagging. By utilizing a sparsely-gated mixture of experts, MoE-VRD enables conditional computation and significantly enhances neural network capacity without increasing computational complexity. Our experimental results demonstrate that the conditional computation capabilities and scalability of the mixture-of-experts approach lead to superior performance in visual relationship detection compared to state-of-the-art methods.
We present a novel self-supervised approach for representation learning, particularly for the task of Visual Relationship Detection (VRD). Motivated by the effectiveness of Masked Image Modeling (MIM), we propose Masked Bounding Box Reconstruction (MBBR), a variation of MIM where a percentage of the entities/objects within a scene are masked and subsequently reconstructed based on the unmasked objects. The core idea is that, through object-level masked modeling, the network learns context-aware representations that capture the interaction of objects within a scene and thus are highly predictive of visual object relationships. We extensively evaluate learned representations, both qualitatively and quantitatively, in a few-shot setting and demonstrate the efficacy of MBBR for learning robust visual representations, particularly tailored for VRD. The proposed method is able to surpass state-of-the-art VRD methods on the Predicate Detection (PredDet) evaluation setting, using only a few annotated samples. We make our code available at https://github.com/deeplab-ai/SelfSupervisedVRD.
Understanding relations between objects is crucial for understanding the semantics of a visual scene. It is also an essential step in order to bridge visual and language models. However, current state-of-the-art computer vision models still lack the ability to perform spatial reasoning well. Existing datasets mostly cover a relatively small number of spatial relations, all of which are static relations that do not intrinsically involve motion. In this paper, we propose the Spatial and Temporal Understanding of Prepositions Dataset (STUPD) -- a large-scale video dataset for understanding static and dynamic spatial relationships derived from prepositions of the English language. The dataset contains 150K visual depictions (videos and images), consisting of 30 distinct spatial prepositional senses, in the form of object interaction simulations generated synthetically using Unity3D. In addition to spatial relations, we also propose 50K visual depictions across 10 temporal relations, consisting of videos depicting event/time-point interactions. To our knowledge, no dataset exists that represents temporal relations through visual settings. In this dataset, we also provide 3D information about object interactions such as frame-wise coordinates, and descriptions of the objects used. The goal of this synthetic dataset is to help models perform better in visual relationship detection in real-world settings. We demonstrate an increase in the performance of various models over 2 real-world datasets (ImageNet-VidVRD and Spatial Senses) when pretrained on the STUPD dataset, in comparison to other pretraining datasets.
This work focuses on training a single visual relationship detector predicting over the union of label spaces from multiple datasets. Merging labels spanning different datasets could be challenging due to inconsistent taxonomies. The issue is exacerbated in visual relationship detection when second-order visual semantics are introduced between pairs of objects. To address this challenge, we propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models (VLMs). VLMs provide well-aligned image and text embeddings, where similar relationships are optimized to be close to each other for semantic unification. Our bottom-up design enables the model to enjoy the benefit of training with both object detection and visual relationship datasets. Empirical results on both human-object interaction detection and scene-graph generation demonstrate the competitive performance of our model. UniVRD achieves 38.07 mAP on HICO-DET, outperforming the current best bottom-up HOI detector by 14.26 mAP. More importantly, we show that our unified detector performs as well as dataset-specific models in mAP, and achieves further improvements when we scale up the model. Our code will be made publicly available on GitHub.
For humans, understanding the relationships between objects using visual signals is intuitive. For artificial intelligence, however, this task remains challenging. Researchers have made significant progress studying semantic relationship detection, such as human-object interaction detection and visual relationship detection. We take the study of visual relationships a step further from semantic to geometric. In specific, we predict relative occlusion and relative distance relationships. However, detecting these relationships from a single image is challenging. Enforcing focused attention to task-specific regions plays a critical role in successfully detecting these relationships. In this work, (1) we propose a novel three-decoder architecture as the infrastructure for focused attention; 2) we use the generalized intersection box prediction task to effectively guide our model to focus on occlusion-specific regions; 3) our model achieves a new state-of-the-art performance on distance-aware relationship detection. Specifically, our model increases the distance F1-score from 33.8% to 38.6% and boosts the occlusion F1-score from 34.4% to 41.2%. Our code is publicly available.
Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions. Since the interactions associated with the same object are dependent, we explore the dependency of interactions to reduce the search space. We explicitly model objects and interactions by an interaction graph and then propose a message-passing-style algorithm to propagate the contextual information. We thus call the proposed method neural message passing (NMP). We further integrate language priors and spatial cues to rule out unrealistic interactions and capture spatial interactions. Experimental results on two benchmark datasets demonstrate the superiority of our proposed method. Our code is available at https://github.com/PhyllisH/NMP.
The single-hidden-layer Randomly Weighted Feature Network (RWFN) introduced by Hong and Pavlic (2021) was developed as an alternative to neural tensor network approaches for relational learning tasks. Its relatively small footprint combined with the use of two randomized input projections -- an insect-brain-inspired input representation and random Fourier features -- allow it to achieve rich expressiveness for relational learning with relatively low training cost. In particular, when Hong and Pavlic compared RWFN to Logic Tensor Networks (LTNs) for Semantic Image Interpretation (SII) tasks to extract structured semantic descriptions from images, they showed that the RWFN integration of the two hidden, randomized representations better captures relationships among inputs with a faster training process even though it uses far fewer learnable parameters. In this paper, we use RWFNs to perform Visual Relationship Detection (VRD) tasks, which are more challenging SII tasks. A zero-shot learning approach is used with RWFN that can exploit similarities with other seen relationships and background knowledge -- expressed with logical constraints between subjects, relations, and objects -- to achieve the ability to predict triples that do not appear in the training set. The experiments on the Visual Relationship Dataset to compare the performance between RWFNs and LTNs, one of the leading Statistical Relational Learning frameworks, show that RWFNs outperform LTNs for the predicate-detection task while using fewer number of adaptable parameters (1:56 ratio). Furthermore, background knowledge represented by RWFNs can be used to alleviate the incompleteness of training sets even though the space complexity of RWFNs is much smaller than LTNs (1:27 ratio).
There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection. Due to the lack of a good benchmark, the reported results of different scene graph generation models are not directly comparable, impeding the research progress. We have developed a much-needed scene graph generation benchmark based on the maskrcnn-benchmark and several popular models. This paper presents main features of our benchmark and a comprehensive ablation study of scene graph generation models using the Visual Genome and OpenImages Visual relationship detection datasets. Our codebase is made publicly available at https://github.com/microsoft/scene_graph_benchmark.
Visual 2.5D perception involves understanding the semantics and geometry of a scene through reasoning about object relationships with respect to the viewer in an environment. However, existing works in visual recognition primarily focus on the semantics. To bridge this gap, we study 2.5D visual relationship detection (2.5VRD), in which the goal is to jointly detect objects and predict their relative depth and occlusion relationships. Unlike general VRD, 2.5VRD is egocentric, using the camera's viewpoint as a common reference for all 2.5D relationships. Unlike depth estimation, 2.5VRD is object-centric and not only focuses on depth. To enable progress on this task, we create a new dataset consisting of 220k human-annotated 2.5D relationships among 512K objects from 11K images. We analyze this dataset and conduct extensive experiments including benchmarking multiple state-of-the-art VRD models on this task. Our results show that existing models largely rely on semantic cues and simple heuristics to solve 2.5VRD, motivating further research on models for 2.5D perception. The new dataset is available at https://github.com/google-research-datasets/2.5vrd.
Analyzing the interactions between humans and objects from a video includes identification of the relationships between humans and the objects present in the video. It can be thought of as a specialized version of Visual Relationship Detection, wherein one of the objects must be a human. While traditional methods formulate the problem as inference on a sequence of video segments, we present a hierarchical approach, LIGHTEN, to learn visual features to effectively capture spatio-temporal cues at multiple granularities in a video. Unlike current approaches, LIGHTEN avoids using ground truth data like depth maps or 3D human pose, thus increasing generalization across non-RGBD datasets as well. Furthermore, we achieve the same using only the visual features, instead of the commonly used hand-crafted spatial features. We achieve state-of-the-art results in human-object interaction detection (88.9% and 92.6%) and anticipation tasks of CAD-120 and competitive results on image based HOI detection in V-COCO dataset, setting a new benchmark for visual features based approaches. Code for LIGHTEN is available at https://github.com/praneeth11009/LIGHTEN-Learning-Interactions-with-Graphs-and-Hierarchical-TEmporal-Networks-for-HOI
Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (iii) robustness to the design choices regarding its computation, and its applicability to outputs without confidence scores. Panoptic Quality (PQ), a measure proposed for evaluating panoptic segmentation (Kirillov et al., 2019), does not suffer from these limitations but is limited to panoptic segmentation. In this paper, we propose Localisation Recall Precision (LRP) Error as the average matching error of a visual detector computed based on both its localisation and classification qualities for a given confidence score threshold. LRP Error, initially proposed only for object detection by Oksuz et al. (2018), does not suffer from the aforementioned limitations and is applicable to all visual detection tasks. We also introduce Optimal LRP (oLRP) Error as the minimum LRP Error obtained over confidence scores to evaluate visual detectors and obtain optimal thresholds for deployment. We provide a detailed comparative analysis of LRP Error with AP and PQ, and use nearly 100 state-of-the-art visual detectors from seven visual detection tasks (i.e. object detection, keypoint detection, instance segmentation, panoptic segmentation, visual relationship detection, zero-shot detection and generalised zero-shot detection) using ten datasets to empirically show that LRP Error provides richer and more discriminative information than its counterparts. Code available at: https://github.com/kemaloksuz/LRP-Error
Visual relationship detection aims to reason over relationships among salient objects in images, which has drawn increasing attention over the past few years. Inspired by human reasoning mechanisms, it is believed that external visual commonsense knowledge is beneficial for reasoning visual relationships of objects in images, which is however rarely considered in existing methods. In this paper, we propose a novel approach named Relational Visual-Linguistic Bidirectional Encoder Representations from Transformers (RVL-BERT), which performs relational reasoning with both visual and language commonsense knowledge learned via self-supervised pre-training with multimodal representations. RVL-BERT also uses an effective spatial module and a novel mask attention module to explicitly capture spatial information among the objects. Moreover, our model decouples object detection from visual relationship recognition by taking in object names directly, enabling it to be used on top of any object detection system. We show through quantitative and qualitative experiments that, with the transferred knowledge and novel modules, RVL-BERT achieves competitive results on two challenging visual relationship detection datasets. The source code is available at https://github.com/coldmanck/RVL-BERT.
Visual relationship detection is fundamental for holistic image understanding. However, localizing and classifying (subject, predicate, object) triplets constitutes a hard learning objective due to the combinatorial explosion of possible relationships, their long-tail distribution in natural images, and an expensive annotation process. This paper introduces a novel weakly-supervised method for visual relationship detection that relies only on image-level predicate annotations. A graph neural network is trained to classify the predicates in an image from the graph representation of all objects, implicitly encoding an inductive bias for pairwise relationships. We then frame relationship detection as the explanation of such a predicate classifier, i.e. we reconstruct a complete relationship by recovering the subject and the object of a predicted predicate. Using this novel technique and minimal labels, we present comparable results to recent fully-supervised and weakly-supervised methods on three diverse and challenging datasets: HICO-DET for human-object interaction, Visual Relationship Detection for generic object-to-object relationships, and UnRel for unusual relationships.
Visual relationship detection aims to locate objects in images and recognize the relationships between objects. Traditional methods treat all observed relationships in an image equally, which causes a relatively poor performance in the detection tasks on complex images with abundant visual objects and various relationships. To address this problem, we propose an attention based model, namely AVR, to achieve salient visual relationships based on both local and global context of the relationships. Specifically, AVR recognizes relationships and measures the attention on the relationships in the local context of an input image by fusing the visual features, semantic and spatial information of the relationships. AVR then applies the attention to assign important relationships with larger salient weights for effective information filtering. Furthermore, AVR is integrated with the priori knowledge in the global context of image datasets to improve the precision of relationship prediction, where the context is modeled as a heterogeneous graph to measure the priori probability of relationships based on the random walk algorithm. Comprehensive experiments are conducted to demonstrate the effectiveness of AVR in several real-world image datasets, and the results show that AVR outperforms state-of-the-art visual relationship detection methods significantly by up to $87.5\%$ in terms of recall.
Semantic image understanding is a challenging topic in computer vision. It requires to detect all objects in an image, but also to identify all the relations between them. Detected objects, their labels and the discovered relations can be used to construct a scene graph which provides an abstract semantic interpretation of an image. In previous works, relations were identified by solving an assignment problem formulated as Mixed-Integer Linear Programs. In this work, we interpret that formulation as Ordinary Differential Equation (ODE). The proposed architecture performs scene graph inference by solving a neural variant of an ODE by end-to-end learning. It achieves state-of-the-art results on all three benchmark tasks: scene graph generation (SGGen), classification (SGCls) and visual relationship detection (PredCls) on Visual Genome benchmark.
Visual relationship detection, as a challenging task used to find and distinguish the interactions between object pairs in one image, has received much attention recently. In this work, we propose a novel visual relationship detection framework by deeply mining and utilizing relative location of object-pair in every stage of the procedure. In both the stages, relative location information of each object-pair is abstracted and encoded as auxiliary feature to improve the distinguishing capability of object-pairs proposing and predicate recognition, respectively; Moreover, one Gated Graph Neural Network(GGNN) is introduced to mine and measure the relevance of predicates using relative location. With the location-based GGNN, those non-exclusive predicates with similar spatial position can be clustered firstly and then be smoothed with close classification scores, thus the accuracy of top $n$ recall can be increased further. Experiments on two widely used datasets VRD and VG show that, with the deeply mining and exploiting of relative location information, our proposed model significantly outperforms the current state-of-the-art.
Semantic Image Interpretation is the task of extracting a structured semantic description from images. This requires the detection of visual relationships: triples (subject,relation,object) describing a semantic relation between a subject and an object. A pure supervised approach to visual relationship detection requires a complete and balanced training set for all the possible combinations of (subject, relation, object). However, such training sets are not available and would require a prohibitive human effort. This implies the ability of predicting triples which do not appear in the training set. This problem is called zero-shot learning. State-of-the-art approaches to zero-shot learning exploit similarities among relationships in the training set or external linguistic knowledge. In this paper, we perform zero-shot learning by using Logic Tensor Networks, a novel Statistical Relational Learning framework that exploits both the similarities with other seen relationships and background knowledge, expressed with logical constraints between subjects, relations and objects. The experiments on the Visual Relationship Dataset show that the use of logical constraints outperforms the current methods. This implies that background knowledge can be used to alleviate the incompleteness of training sets.
Visual relation detection methods rely on object information extracted from RGB images such as 2D bounding boxes, feature maps, and predicted class probabilities. We argue that depth maps can additionally provide valuable information on object relations, e.g. helping to detect not only spatial relations, such as standing behind, but also non-spatial relations, such as holding. In this work, we study the effect of using different object features with a focus on depth maps. To enable this study, we release a new synthetic dataset of depth maps, VG-Depth, as an extension to Visual Genome (VG). We also note that given the highly imbalanced distribution of relations in VG, typical evaluation metrics for visual relation detection cannot reveal improvements of under-represented relations. To address this problem, we propose using an additional metric, calling it Macro Recall@K, and demonstrate its remarkable performance on VG. Finally, our experiments confirm that by effective utilization of depth maps within a simple, yet competitive framework, the performance of visual relation detection can be improved by a margin of up to 8%.