Search Results for author:
Found 28 papers, 5 papers with code
Structured Visual Search via Composition-aware Learning
The structure is in the form of a 2D composition that encodes the position and the category of the objects.
Tackling Occlusion in Siamese Tracking with Structured Dropouts
Specifically, we present structured dropout to mimick the change in latent codes under occlusion.
PIC: Permutation Invariant Convolution for Recognizing Long-range Activities
We study the three properties of PIC and demonstrate its effectiveness in recognizing the long-range activities of Charades, Breakfast, and MultiThumos.
Cloth in the Wind: A Case Study of Physical Measurement through Simulation
For many of the physical phenomena around us, we have developed sophisticated models explaining their behavior.
Go with the Flow: Perception-refined Physics Simulation
Nevertheless, inferring specifics from visual observations is challenging due to the high number of causally underlying physical parameters -- including material properties and external forces.
Model Decay in Long-Term Tracking
Updating the tracker model with adverse bounding box predictions adds an unavoidable bias term to the learning.
VideoGraph: Recognizing Minutes-Long Human Activities in Videos
To represent them, related works opt for statistical pooling, which neglects the temporal structure.
Ranked #6 on
Long-video Activity Recognition
on Breakfast
Cooperative Embeddings for Instance, Attribute and Category Retrieval
These relationships enable them to cooperate for their mutual benefits for image retrieval.
Timeception for Complex Action Recognition
This paper focuses on the temporal aspect for recognizing human activities in videos; an important visual cue that has long been undervalued.
Ranked #6 on
Video Classification
on Breakfast
Estimating Small Differences in Car-Pose from Orbits
The generated orbit in the latent space records all the differences in pose in the original observational space, and as a result, the method is capable of finding subtle differences in pose.
Repetition Estimation
Estimating visual repetition from realistic video is challenging as periodic motion is rarely perfectly static and stationary.
Featureless: Bypassing feature extraction in action categorization
This method introduces an efficient manner of learning action categories without the need of feature estimation.
Deja Vu: Motion Prediction in Static Images
This paper proposes motion prediction in single still images by learning it from a set of videos.
Asymmetric kernel in Gaussian Processes for learning target variance
This enables each center to adjust the kernel space in its vicinity in correspondence with the topology of the targets --- a multi-modal approach.
Real-World Repetition Estimation by Div, Grad and Curl
We consider the problem of estimating repetition in video, such as performing push-ups, cutting a melon or playing violin.
Tracking for Half an Hour
Long-term tracking requires extreme stability to the multitude of model updates and robustness to the disappearance and loss of the target as such will inevitably happen.
Tracking by Natural Language Specification
This paper strives to track a target object in a video.
Ranked #17 on
Referring Expression Segmentation
on J-HMDB
Dynamic Steerable Blocks in Deep Residual Networks
Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account.
Unified Embedding and Metric Learning for Zero-Exemplar Event Detection
Given a text describing a novel event, the goal is to rank related videos accordingly.
Multiscale Hierarchical Convolutional Networks
Multiscale hierarchical convolutional networks are structured deep convolutional networks where layers are indexed by progressively higher dimensional attributes, which are learned from training data.
Generating captions without looking beyond objects
This paper explores new evaluation perspectives for image captioning and introduces a noun translation task that achieves comparative image caption generation performance by translating from a set of nouns to captions.
Searching Scenes by Abstracting Things
Second, we propose translating the things syntax in linguistic abstract statements and study their descriptive effect to retrieve scenes.
Generic Instance Search and Re-identification from One Example via Attributes and Categories
Searching among instances from the same category as the query, the category-specific attributes outperform existing approaches by a large margin on shoes and cars and perform on par with the state-of-the-art on buildings.
Siamese Instance Search for Tracking
In this paper we present a tracker, which is radically different from state-of-the-art trackers: we apply no model updating, no occlusion detection, no combination of trackers, no geometric matching, and still deliver state-of-the-art tracking performance, as demonstrated on the popular online tracking benchmark (OTB) and six very challenging YouTube videos.
Structured Receptive Fields in CNNs
We combine these ideas into structured receptive field networks, a model which has a fixed filter basis and yet retains the flexibility of CNNs.
Attributes and Categories for Generic Instance Search From One Example
This paper aims for generic instance search from one example where the instance can be an arbitrary 3D object like shoes, not just near-planar and one-sided instances like buildings and logos.
Fisher and VLAD with FLAIR
Finally, by multiple codeword assignments, we achieve exact and approximate Fisher vectors with FLAIR.
Locality in Generic Instance Search from One Example
This paper aims for generic instance search from a single example.
